How to run Qwen 3.5 locally

490 points by Curiositry 94 days ago | 168 comments

moqizhengz 93 days ago |

Running 3.5 9B on my ASUS 5070ti 16G with lm studio gives a stable ~100 tok/s. This outperforms the majority of online llm services and the actual quality of output matches the benchmark. This model is really something, first time ever having usable model on consumer-grade hardware.

smokel 93 days ago | |

> This outperforms the majority of online llm services

I assume you mean outperforms in speed on the same model, not in usability compared to other more capable models.

(For those who are getting their hopes up on using local LLMs to be any replacement for Sonnet or Opus.)

moffkalast 93 days ago | | |

Obviously it's not going to be of a paid tier 2T sized SOTA model quality, but it can probably roughly match Haiku at the very least. And for tasks that aren't super complex that's already enough.

Personally though, I find Qwen useless for anything but coding tasks because if its insufferable sycophancy. It's like 4o dialed up to 20, every reply starts with "You are absolutely right" with zero self awareness. And for coding, only the best model available is usually sensible to use otherwise it's just wasted time.

segmondy 93 days ago | | |

You can replace Sonnet and Opus with local models, you just need to run the larger ones.

throwdbaaway 93 days ago | |

There are Qwen3.5 27B quants in the range of 4 bits per weight, which fits into 16G of VRAM. The quality is comparable to Sonnet 4.0 from summer 2025. Inference speed is very good with ik_llama.cpp, and still decent with mainline llama.cpp.

codemog 93 days ago | | |

Can someone explain how a 27B model (quantized no less) ever be comparable to a model like Sonnet 4.0 which is likely in the mid to high hundreds of billions of parameters?

Is it really just more training data? I doubt it’s architecture improvements, or at the very least, I imagine any architecture improvements are marginal.

zozbot234 93 days ago | | |

With MoE models, if the complete weights for inactive experts almost fit in RAM you can set up mmap use and they will be streamed from disk when needed. There's obviously a slowdown but it is quite gradual, and even less relevant if you use fast storage.

teaearlgraycold 93 days ago | | |

Qwen3.5 35B A3B is much much faster and fits if you get a 3 bit version. How fast are you getting 27B to run?

On my M3 Air w/ 24GB of memory 27B is 2 tok/s but 35B A3B is 14-22 tok/s which is actually usable.

ljosifov 93 days ago | | |

Say more please if you can. How/why is ik_llama.cpp faster then mainline, for the 27B dense? I'd like to be able to run 27B dense faster on a 24GB vram gpu, and also on an M2 max.

the_duke 93 days ago | |

What context length and related performance are you getting out if this setup?

At least 100k context without huge degradation is important for coding tasks. Most "I'm running this locally" reports only cover testing with very small context.

Aurornis 93 days ago | | |

Long context degradation is a problem with the Qwen3.5 models for me. They have some clever tricks to accelerate attention that favor more recent context.

The models can be frustrating to use if you expect long contexts to behave like they do on SOTA models. In my trials I could give them strict instructions to NOT do something and they would follow it for a short time before ignoring my prompt and doing the things I told it not to do.

vardalab 93 days ago | | |

Q4 quants on 32G VRAM gives you 131K context for 35BA3B and 27B models who are pretty capable. On 5090 one gets 175 tg and ~7K pp with 35BA3B, 27B isaround 90 tg. So speed is awesome. Even Strix 395 gives 40 tk/s and 256K context. Pretty amazing, there is a reason people are excited about qwen 3.5

lukan 93 days ago | |

What exact model are you using?

I have a 16GB GPU as well, but have never run a local model so far. According to the table in the article, 9B and 8-bit -> 13 GB and 27B and 3-bit seem to fit inside the memory. Or is there more space required for context etc?

vasquez 93 days ago | | |

It depends on the task, but you generally want some context. These models can do things like OCR and summarize a pdf for you, which takes a bit of working memory. Even more so for coding CLIs like opencode-ai, qwen code and mistral ai.

Inference engines like llama.cpp will offload model and context to system ram for you, at the cost of performance. A MoE like 35B-A3B might serve you better than the ones mentioned, even if it doesn't fit entirely on the GPU. I suggest testing all three. Perhaps even 122-A10B if you have plenty of system ram.

Q4 is a common baseline for simple tasks on local models. I like to step up to Q5/Q6 for anything involving tool use on the smallish models I can run (9B and 35B-A3B).

Larger models tolerate lower quants better than small ones, 27B might be usable at 3 bpw where 9B or 4B wouldn't. You can also quantize the context. On llama.cpp you'd set the flags -fa on, -ctk x and ctv y. -h to see valid parameters. K is more sensitive to quantization than V, don't bother lowering it past q8_0. KV quantization is allegedly broken for Qwen 3.5 right now, but I can't tell.

yangikan 93 days ago | |

Do you point claude code to this? The orchestration seems to be very important.

tommyjepsen 93 days ago | | |

I ran the Qwen3 Coder 30B through LM Studio and with OpenCode(Instead of Claude code). Did decent on M4 Max 32GB. https://www.tommyjepsen.com/blog/run-llm-locally-for-coding

Aurornis 93 days ago | | |

The 9B models are not useful for coding outside of very simple requests.

Qwen3.5 is confusing a lot of newcomers because it is very confident in the answers it gives. It can also regurgitate solutions to common test requests like “make a flappy bird clone” which misleads users into thinking it’s genetically smart.

Using the Qwen3.5 models for longer tasks and inspecting the output is a little more disappointing. They’re cool for something I can run locally but I don’t agree with all of the claims about being Sonnet-level quality (including previous Sonnet versions) in my experience with the larger models. The 9B model is not going to be close to Sonnet in any way.

teaearlgraycold 93 days ago | | |

I loaded Qwen into LM Studio and then ran Oh My Pi. It automatically picked up the LM Studio API server. For some reason the 35B A3B model had issues with Oh My Pi's ability to pass a thinking parameter which caused it to crash. 27B did not have that issue for me but it's much slower.

Here's how I got the 35B model to work: https://gist.github.com/danthedaniel/c1542c65469fb1caafabe13...

The 35B model is still pretty slow on my machine but it's cool to see it working.

badgersnake 93 days ago | | |

I’ve tried it on Claude code, Found it to be fairly crap. It got stuck in a loop doing the wrong thing and would not be talked out of it. I’ve found this bug that would stop it compiling right after compiling it, that sort of thing.

Also seemed to ignore fairly simple instructions in CLAUDE.md about building and running tests.

andsoitis 93 days ago | | |

I use Claude Code for agentic coding but it is better to use qwen3-coder in that case.

It qwen3-coder is better for code generation and editing, strong at multi-file agentic tasks, and is purpose-built for coding workflows.

In contrast, qwen3.5 is more capable at general reasoning, better at planning and architecture decisions, good balance of coding and thinking.

jadbox 93 days ago | |

Did you figure out how to fix Thinking mode? I had to turn it off completely as it went on forever, and I tried to fix it with different parameters without success.

sammyteee 93 days ago | | |

Thinking has definitely become a bit more convuluted in this model - I gave the prompt of "hey" and it thought for about two minutes straight before giving a bog-standard "hello, how can i help" reply etc

andrekandre 93 days ago | | |

supposedly you can turn it off by passing `\no_think` or `/no_think` into the prompt but it never worked for me

what did work was passing / adding this json to the request body:

   { "chat_template_kwargs": {"enable_thinking": false}}

[0] https://github.com/QwenLM/Qwen3/discussions/1300

agile-gift0262 92 days ago | | |

did you try with the recommended settings? the ones for thinking mode, general tasks, really worked for me. Especially the repetition_penalty. At first it wasn't working very well, and it was because I was using OpenWebUI's "Repeat Penalty" field, and that didn't work. I needed to set a custom field with the exact name

bluerooibos 93 days ago | |

These smaller models are fine for Q&A type stuff but are basically unuseable for anything agentic like large file modifications, coding, second brain type stuff - they need so much handholding. I'd be interested to see a demo of what the larger versions can do on better hardware though.

NorwegianDude 93 days ago | | |

Qwen3.5 27B works very well, to the point that if you use money on Claude 4.5 Haiku you could save hundreds of USD each day by running it yourself on a consumer GPU at home.

regularfry 93 days ago | | |

In some ways the handholding is the point. The way I used qwen2.5-coder in the past was as a rubber duck that happens to be able to type. You have to be in the loop with it, it's just a different style of agent use to what you might do with copilot or Claude.

y42 93 days ago | |

> consumer-grade hardware

Not disagreeing per se, but a quick look at the installation instructions confirms what I assumed:

Yeah, you can run a highly quantized version on your 2020 Nvidia GPU. But:

- When inferencing, it occupies your "whole machine.". At least you have a modern interactive heating feature in your flat.

- You need to follow eleven-thousand nerdy steps to get it running; my mum is really looking forward to that.

- Not to mention the pain you went through installing Nvidia drivers; nothing my mum will ever manage in the near future.

... and all this to get something that merely competes with Haiku.

Don't get me wrong - I am exaggerating, I know. It's important to have competition and the opportunity to run "AI" on your own metal. But this reminds me of the early days of smartphones and my old XDA Neo. Sure, it was damn smart, and I remember all those jealous faces because of my "device from the future." But oh boy, it was also a PITA maintaining it.

Here we are now. Running AI locally is a sneak peek into the future. But as long as you need a CS degree and hardware worth a small car to achieve reasonable results, it's far from mainstream. Therefore, "consumer-grade hardware" sounds like a euphemism here.

I like how we nerds are living in our buble celebrating this stuff while 99% of mankind still doomscroll through facebook and laughing at (now AI generated) brain rot.

(No offense (ʘ‿ʘ)╯)

mingodad 93 days ago |

I'm still a bit confused because it says "All uploads use Unsloth Dynamic 2.0" but then when looking at the available options like for 4 bits there is:

IQ4_XS 5.17 GB, Q4_K_S 5.39 GB, IQ4_NL 5.37 GB, Q4_0 5.38 GB, Q4_1 5.84 GB, Q4_K_M 5.68 GB, UD-Q4_K_XL 5.97 GB

And no explanation for what they are and what tradeoffs they have, but in the turorial it explicitly used Q4_K_XL with llama.cpp .

I'm using a macmini m4 16GB and so far my prefered model is Qwen3-4B-Instruct-2507-Q4_K_M although a bit chat but my test with Qwen3.5-4B-UD-Q4_K_XL shows it's a lot more chat, I'm basically using it in chat mode for basic man style questions.

I understand that each user has it's own specific needs but would be nice to have a place that have a list of typical models/hardware listed with it's common config parameters and memory usage.

Even on redit specific channels it's a bit of nightmare of loot of talk but no concrete config/usage clear examples.

I'm floowing this topic heavilly for the last 3 months and I see more confusion than clarification.

Right now I'm getting good cost/benefit results with the qwen cli with coder-model in the cloud and watching constantly to see when a local model on affordable hardware with enviroment firendly energy comsumption arrives.

antirez 93 days ago |

My private benchmarks, using DeepSeek replies to coding problems as a baseline, with Claude Opus as judge. However when reading this percentages consider that the no-think setup is much faster, and may be more practical for most situations.

    1   │ DeepSeek API -- 100%
    2   │ qwen3.5:35b-a3b-q8_0 (thinking) -- 92.5%
    3   │ qwen3.5:35b-a3b-q4_K_M (thinking) -- 90.0%
    4   │ qwen3.5:35b-a3b-q8_0 (no-think) -- 81.3%
    5   │ qwen3.5:27b-q8_0 (thinking) -- 75.3%

I expected the 27B dense model to score higher. Disclaimer: those numbers are from one-shot replies evaluations, the model was not put in a context where it could reiterate as an agent.

throwdbaaway 93 days ago | |

Yours is the only benchmark that puts 35B A3B above 27B. Time for human judgement to verify? For example, if you look at the thinking traces, there might be logical inconsistencies in the prompts, which then tripped up the 27B more when reasoning. This will also be reflected in the score when thinking is disabled, but we can sort of debug with the thinking traces.

antirez 93 days ago | | |

I inspected manually and indeed the 27B is doing worse, but I believe it could be due to the exact GGUF in the ollama repository and/or with the need of adjusting the parameters. I'll try more stuff.

alansaber 93 days ago | |

Maybe a reductive question but are there any thinking models that don't (relatively) add much latency?

ac29 93 days ago | | |

The whole point of thinking is to throw more compute/tokens at a problem, so it will always add latency over non thinking modes/models. Many models do support variable thinking levels or thinking token budgets though, so you can set them to low/minimal thinking if you want only a minimal increase in latency versus no thinking.

d4rkp4ttern 93 days ago |

For every new interesting open model I try to test PP (prompt processing) and TG (token gen) speeds via llama-cpp/server in Claude Code (which can have at least 15-30K tokens context due system prompt and tools etc), on my good old M1 Max 64GB MacBook.

With the latest llama-cpp build from source and latest unsloth quants, the TG speed of Qwen3.5-30B-A3B is around half of Qwen3-30B-A3B (with 33K tokens initial Claude Code context), so the older Qwen3 is much more usable.

Qwen3-30B-A3B (Q4_K_M):

  - PP: 272 tok/s | TG: 25 tok/s @ 33k depth

  - KV cache: f16

  - Cache reuse: follow-up delta processed in 0.4s

Qwen3.5-35B-A3B (Q4_K_M):

  - PP: 395 tok/s | TG: 12 tok/s @ 33k depth

  - KV cache: q8_0

  - Cache reuse: follow-up delta processed in 2.7s (requires --swa-full)

Qwen3.5's sliding window attention uses significantly less RAM and delivers better response quality, but at 33k context depth it generates at half the tok/s of the standard-attention Qwen3-30B.

Full llama-server and Claude-Code setup details here for these and other open LLMs:

https://pchalasani.github.io/claude-code-tools/integrations/...

regularfry 93 days ago | |

I definitely get the impression there's something not quite right with qwen3.5 in llama.cpp. It's impressive but just a bit off. A patch landed yesterday which helped though.

ranger_danger 92 days ago | | |

Which patch are you referring to?

Twirrim 93 days ago |

I've been finding it very practical to run the 35B-A3B model on an 8GB RTX 3050, it's pretty responsive and doing a good job of the coding tasks I've thrown at it. I need to grab the freshly updated models, the older one seems to occasionally get stuck in a loop with tool use, which they suggest they've fixed.

Curiositry 93 days ago |

Qwen3.5 9b seems to be fairly competent at OCR and text formatting cleanup running in llama.cpp on CPU, albeit slow. However, I have compiled it umpteen ways and still haven't gotten GPU offloading working properly (which I had with Ollama), on an old 1650 Ti with 4GB VRAM (it tries to allocate too much memory).

acters 93 days ago | |

I have a 1660ti and the cachyos + aur/llama.cpp-cuda package is working fine for me. With about 5.3 GB of usable memory, I find that the 35B model is by far the most capable one that performs just as fast as the 4B model that fits entirely on my GPU. I did try the 9B model and was surprisingly capable. However 35B still better in some of my own anecdotal test cases. Very happy with the improvement. However, I notice that qwen 3.5 is about half the speed of qwen 3

AllegedAlec 92 days ago | |

I found that the drivers I had were no longer compatible with the newer kernels. After upgrading to newer drivers it was able to offload again.

dunb 93 days ago | |

Are you running with all the --fit options and it’s not working correctly? You could try looking at how many layers are being attempted to offload and manually adjust from there. Walk down --n-gpu-layers with a bash script until it loads.

lioeters 93 days ago | |

> GPU offloading working

I had this issue which in my case was solved by installing a newer driver. YMMV.

  sudo apt install nvidia-driver-570

WhyNotHugo 93 days ago | |

If you’re building from source, the vulkan backend is the easiest to build and use for GPU offloading.

Curiositry 93 days ago | | |

Yes, that's what I tried first. Same issue with trying to allocate more memory than was available.

tasuki 93 days ago |

How does one choose between "fewer parameters and less quantization" vs "more parameters and more quantization" ?

labcomputer 93 days ago | |

There were some benchmarks a few years ago from, IIRC, the people behind either llama.cpp or Ollama (I forget which).

The basic rule of thumb is that more parameters is always better, with diminishing returns as you get down to 2-3 bits per parameter. This is purely based on model quality, not inference speed.

paoliniluis 93 days ago | |

just finding the perfect spot between accuracy of the answers/available VRAM/tokens per second

tasuki 93 days ago | | |

Ok, say I have 14GB VRAM. What is the tradeoff between using 9B with 8-bit params vs 27B with 3-bit params?

PeterStuer 93 days ago |

I am running both Qwen-coder-next and Qwen 3.5 locally. Not too bad, but I always have Opus 4.6 checking their output as the Qwen family tends to hallucinate non existing library features in amounts similar to the Claude 3.5 / GPT 4 era.

The combo of free long running tasks on Qwen overnight with steering and corrections from Opus works for me.

I guess I could just do Opus/Sonnet for my Claude Code back-end, but I specifically want to keep local open weights models in the loop just in case the hosted models decide to quit on e.g. non-US users.

brcmthrowaway 93 days ago | |

How did they solve the hallucination? Reasoning tokens?

b89kim 93 days ago |

I’ve been benchmarking GGUF quants for Python tasks under some hardware configs.

  - 4090 : 27b-q4_k_m
  - A100: 27b-q6_k
  - 3*A100: 122b-a10b-q6_k_L

Using the Qwen team's "thinking" presets, I found that non-agentic coding performance doesn't feel significant leap over unquantized GPT-OSS-120B. It shows some hallucination and repetition for mujoco codes with default presence penalty. 27b-q4_k_m with 4090 generates 30~35 tok/s in good quality.

dryarzeg 93 days ago | |

That's quite a specific task for local models like these though (I mean mujoco), so it might be underrepresented in the training data or RL. I'm not sure if you will be able to see a significant leap in this direction in the next 0.5-2 years, although it's still possible.

b89kim 93 days ago | | |

I’ve been testing these on other tasks—IK, Kalman filters, and UI/DB boilerplate. Qwen3.5 is multimodal and specialized for js/webdev or agentic coding. It’s not surprising MoE model have some limitations in specific area. I understand most LLM have limited ability in mathematical/physical reasoning. And I don't think these tasks represent general performance. I'm just sharing personal experiences for those curious.

_qua 93 days ago |

For roughly equivalent memory sizes, how does one choose between the bit depth and the model size?

moffkalast 93 days ago | |

As a rule of thumb the larger the model is, the more you can quantize it without losing performance, but smaller models will run faster. It usually always makes sense to pick the larger model at a lower quant, as long as the speed is acceptable. Smaller models also use a smaller KV cache, so longer contexts are more viable. It really depends on what your use case is.

Imo though, going below 4 bits for anything that's less than 70B is not worth the degradation. BF/FP16 and Q8 are usually indistinguishable except for vision encoders (mmproj) and for really small models, like under 2B.

jedisct1 93 days ago |

Qwen3.5-27B works amazingly well with https://swival.dev now that the unsloth quants have fixed the tool calling issues.

I still like and mainly use Qwen3-Coder-Next, though, as it seems to be generally more reliable.

adsharma 93 days ago |

So many variants of these models. The ggufs from unsloth don't work with ollama. Perhaps wait for a bit for the latest llama.cpp to be picked up by downstream projects.

If you're on a 16GB Mac mini, what's a good variant to run?

rurban 93 days ago |

We did run it locally on a free H100, and it performed awfully. With vLLM and opencode. Now we are running gpt-oss-120b which is better, but still far behind opus 4.6, the only coding model which is better than our most experienced senior dev. gpt-5.3-codex is more like on the sonnet level on complicated C code. Bearable, but still many stupidities. gpt-oss is hilariously stupid, but might work for typescript, react, python simple tasks.

For vision qwen is the best, our goto vision model.

reissbaker 93 days ago | |

How does it compare at vision tasks to Kimi K2.5?

veritascap 93 days ago |

How does scaffolding work with these local models? Skills, commands, rules, etc. do they all work similarly? (It’s probably obvious but I haven’t delved into local LLMs yet.)

vvram 93 days ago |

What would be optimal HW configurations/systems recommended?

speedgoose 93 days ago | |

It depends. Gaming PCs are fine for small models. Apple hardware can run much bigger models without having to open a window to cool down the room. If money isn’t an issue, NVIDIA isn’t that overpriced for no reasons and a server full of NVIDIA AI GPUs is neat.

benbojangles 93 days ago |

I'm running Qwen3.5:0.8b locally on an Orangepi Zero 2w using llama.cpp, runs just fine on cpu only. If I want vulkan GPU I have run qwen3.5:2b locally on a meta quest 3 with zeroclaw and saved myself hundreds of $$$ buying a low power computer. I recommend people stop shopping around for inflated mac minis and look at getting a used android phone to load local models on.

ilaksh 93 days ago |

Anyone providing hosted inference for 9B? I'm just trying to save the operational effort of renting a GPU since this is a business use case that doesn't have real GPUs available right now. I don't see the small ones on OpenRouter. Maybe there will be a runpod serverless or normal pod template or something.

Also does 9b or 9b 8 bit or 6bit run with very low latency on a 4090?

mongrelion 92 days ago | |

By anyone do you mean a well-established business or any entity willing to serve you?

RandomGerm4n 93 days ago |

9b with 4bits runs with around 60 tok/s on my RTX 4070 with 12GB VRAM and 35b-A3B runs with around 14 tok/s and partial offloading. For roleplaying I prefer the faster 9b Version but for coding tasks both aren't really usable and Claude is still way better especially if you manage to persuade your employer to give you unlimited access.

ac29 93 days ago | |

> 35b-A3B runs with around 14 tok/s and partial offloading

FYI, this is what I am seeing for pure CPU inference so something is likely off with your setup.

Test setup is intel 13500 w/ 6 threads and 64GB DDR4 ram, a newer system should be much faster

edg5000 93 days ago |

How does 397B-A17B compare against frontier? Did anybody try? Probably needs serious HW that most people don't have.

sosodev 93 days ago | |

I’ve tried it via openrouter. It’s very good, but for some tasks frontier models are still significantly better.

For me, the 122b model is good enough on my own hardware that the downsides can be worked around for the sake of privacy and cost savings.

latrine5526 92 days ago |

I have a 5090d and got ~140 token/s output when running qwen-3.5-9b-heretic in lmstudio.

I disabled the thinking and configured the translate plugin on my browser to use the lmstudio API.

It performs way better than Google Translate in accuracy. The speed is a little slower, but sufficient for me.

sieste 93 days ago |

> you can use 'true' and 'false' interchangeably.

made me laugh, especially in the context of LLMs.

computerex 92 days ago |

You can use my new golang inference engine to run variants of Qwen 3.5 faster than llama.cpp: https://github.com/computerex/dlgo

jadbox 93 days ago |

Using llama.cpp and the 9b q4 xl model, it is on Thinking mode by default and runs without stopping. The only way to force it to stop is to set the thinking budget to -1. (Which is weird as the docs say 0 should be valid)

singpolyma3 93 days ago |

Does anyone know what the quantization is with ollama models? They always just list parameter count.

I'm also a bit unsure of the trade offs between smaller quant vs smaller model

paoliniluis 93 days ago | |

run ollama show <name_of_model>:<parameters> and you'll get the info. E.g. ollama show qwen3.5:0.8b Model architecture qwen35 parameters 873.44M context length 262144 embedding length 1024 quantization Q8_0 requires 0.17.1

  Capabilities
    completion    
    vision        
    tools         
    thinking      

  Parameters
    presence_penalty    1.5     
    temperature         1       
    top_k               20      
    top_p               0.95    

  License
    Apache License               
    Version 2.0, January 2004

xrd 93 days ago |

I wanted to submit a fix to the site as I couldn't compile llama.cpp without `sudo apt install nvidia-cuda-toolkit-gcc`. Anyone know where to do that?

kdmtctl 93 days ago |

Will it run on an old 4xV100 Tesla rig? Looking something to start with, this can be available, but too inexperienced to understand all fp* nuances.

chr15m 93 days ago |

It's also working in Ollama now. The 27B model is absolutely cracked on an RTX 3090. Feels close to frontier American models for writing code.

segmondy 93 days ago |

It's truly an amazing model from the small models all the way to 397B. I wish they had released one as a FIM model.

brainless 93 days ago |

Local models, particularly the new ones would be really useful in many situations. They are not for general chat but if tools use them in specific agents, the results are awesome.

I built https://github.com/brainless/dwata to submit for Google Gemini Hackathon, and focused on an agent that would replace email content with regex to extract financial data. I used Gemini 3 Flash.

After submitting to the contest, I kept working on branch: reverse-template-based-financial-data-extraction to use Ministral 3:3b. I moved away from regex detection to a reverse template generation. Like Jinja2 syntax but in reverse, from the source email.

Financial data extraction now works OK ish and I am constantly improving this to aim for a launch soon. I will try with Qwen 3.5 Small, maybe 4b model. Both Ministral 3:3b and Qwen 3.5 Small:4b will fit on the smallest Mac Mini M4 or a RTX 3060 6GB (I have these devices). dwata should be able to process all sorts of financial data, transaction and meta-data (vendor, reference #), at a pretty nice speed. Keep it running a couple hours and you can go through 20K or 30K emails. All local!

gwangee 93 days ago |

Qwen 3.5 is a really good local model. I'm using it with personal assistant(https://github.com/daegwang/atombot) every day!

KronisLV 93 days ago |

I had an annoying issue in a setup with two Nvidia L4 cards where trying to run the MoE versions to get decent performance just didn't work with Ollama, seems the same as these:

https://github.com/ollama/ollama/issues/14419

https://github.com/ollama/ollama/issues/14503

So for now I'm back to Qwen 3 30B A3B, kind of a bummer, because the previous model is pretty fast but kinda dumb, even for simple tasks like on-prem code review!

bradley13 93 days ago |

I have it running locally, but speed is a problem. I have the 35GB model running on a PC with 64GB, a fairly new processor and a mid-level GPU. Ask a question, go drink a coffee.

I mean, it's great that so many models are open-source and readily available. That is hugely important. Running models locally protects your data. But speed is a problem, and likely to remain a problem for the foreseeable future.

Western0 93 days ago |

1. how creating image on small 7-12B LLM 2. how creating a voice

3. how earning bilion dolars in 2 week?

lasgawe 93 days ago |

a clear guide. thanks for that.

$ ./llama.cpp/build/bin/llama-server --host 0.0.0.0 \ --port 8001 \ -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q3_K_S \ --ctx-size 131072 \ --temp 0.6 \ --top-p 0.95 \ --top-k 20 \ --min-p 0.00