For local runs, I made some GGUFs! You need around RAM + VRAM >= 250GB for good perf for dynamic 2bit (2bit MoE, 6-8bit rest) - can also do SSD offloading but it'll be slow.
Looks like it doesn't get close to GPT-5, Claude 4, or GLM-4.5, but still does reasonably well compared to other open weight models. Benchmarks are rarely the full story though, so time will tell how good it is in practice.
garbage benchmark, inconsistent mix of "agent tools" and models. if you wanted to present a meaningful benchmark, the agent tools will stay the same and then we can really compare the models.
there are plenty of other benchmarks that disagree with these, with that said. from my experience most of these benchmarks are trash. use the model yourself, apply your own set of problems and see how well it fairs.
I remember asking for quotes about the Spanish conquest of South America because I couldn't remember who said a specific thing. The GPT model started hallucinating quotes on the topic, while DeepSeek responded with, "I don't know a quote about that specific topic, but you might mean this other thing." or something like that then cited a real quote in the same topic, after acknowledging that it wasn't able to find the one I had read in an old book.
i don't use it for coding, but for things that are more unique i feel is more precise.
I wonder if Conway's law is at all responsible for that, in the similarity it is based on; regional trained data which has concept biases which it sends back in response.
It's a hybrid reasoning model. It's good with tool calls and doesn't think too much about everything, but it regularly uses outdated tool formats randomly instead of the standard JSON format. I guess the V3 training set has a lot of those.
What formats? I thought the very schema of json is what allows these LLMs to enforce structured outputs at the decoder level? I guess you can do it with any format, but why stray from json?
Sometimes it will randomly generate something like this in the body of the text:
```
<tool_call>executeshell
<arg_key>command</arg_key>
<arg_value>echo "" >> novels/AI_Voodoo_Romance/chapter-1-a-new-dawn.txt</arg_value>
</tool_call>
```
or this:
```
<｜toolcallsbegin｜><｜toolcallbegin｜>executeshell<｜toolsep｜>{"command": "pwd && ls -la"}<｜toolcallend｜><｜toolcallsend｜>
```
Prompting it to use the right format doesn't seem to work. Claude, Gemini, GPT5, and GLM 4.5, don't do that. To accomodate DeepSeek, the tiny agent that I'm building will have to support all the weird formats.
Those Qwen3 2507 models are the local creme-de-la-creme right now. If you've got any sort of GPU and ~32gb of RAM to play with, the A3B one is great for pair-programming tasks.
Do you happen to know if it can be run via an eGPU enclosure with f.ex. RTX 5090 inside, under Linux?
I'm considering buying a Linux workstation lately and I want it full AMD. But if I can just plug an NVIDIA card via an eGPU card for self-hosting LLMs then that would be amazing.
I’m running Ollama on 2 eGPUs over Thunderbolt. Works well for me. You’re still dealing with an NVDIA device, of course. The connection type is not going to change that hassle.
Thank you for the validation. As much as I don't like NVIDIA's shenanigans on Linux, having a local LLM is very tempting and I might put my ideological problems to rest over it.
Though I have to ask: why two eGPUs? Is the LLM software smart enough to be able to use any combination of GPUs you point it at?
You would still need drivers and all the stuff difficult with nvidia in linux with a egpu. (Its not nessecarily terrible just suboptimal) Rather just add the second GPU in the Workstation, or just run the llm in your AMD GPU.
I've been running LLM models on my Radeon 7600 XT 16GB for past 2-3 months without issues (Windows 11). I've been using llama.cpp only. The only thing from AMD I installed (apart from latest Radeon drivers) is the "AMD HIP SDK" (very straight forward installer). After unzipping (the zip from GitHub releases page must contain hip-radeon in the name) all I do is this:
llama-server.exe -ngl 99 -m Qwen3-14B-Q6_K.gguf
And then connect to llamacpp via browser to localhost:8080 for the WebUI (its basic but does the job, screenshots can be found on Google). You can connect more advanced interfaces to it because llama.cpp actually has OpenAI-compatible API.
Sure, though you'll be bottlenecked by the interconnect speed if you're tiling between system memory and the dGPU memory. That shouldn't be an issue for the 30B model, but would definitely be an issue for the 480B-sized models.
For local runs, I made some GGUFs! You need around RAM + VRAM >= 250GB for good perf for dynamic 2bit (2bit MoE, 6-8bit rest) - can also do SSD offloading but it'll be slow.
./llama.cpp/llama-cli -hf unsloth/DeepSeek-V3.1-GGUF:UD-Q2_K_XL -ngl 99 --jinja -ot ".ffn_.*_exps.=CPU"
More details on running + optimal params here: https://docs.unsloth.ai/basics/deepseek-v3.1
For reference, here is the terminal-bench leaderboard:
https://www.tbench.ai/leaderboard
Looks like it doesn't get close to GPT-5, Claude 4, or GLM-4.5, but still does reasonably well compared to other open weight models. Benchmarks are rarely the full story though, so time will tell how good it is in practice.
garbage benchmark, inconsistent mix of "agent tools" and models. if you wanted to present a meaningful benchmark, the agent tools will stay the same and then we can really compare the models.
there are plenty of other benchmarks that disagree with these, with that said. from my experience most of these benchmarks are trash. use the model yourself, apply your own set of problems and see how well it fairs.
My personal experience is that it produces high quality results.
Any example or prompt you use to make this statment?
I remember asking for quotes about the Spanish conquest of South America because I couldn't remember who said a specific thing. The GPT model started hallucinating quotes on the topic, while DeepSeek responded with, "I don't know a quote about that specific topic, but you might mean this other thing." or something like that then cited a real quote in the same topic, after acknowledging that it wasn't able to find the one I had read in an old book. i don't use it for coding, but for things that are more unique i feel is more precise.
I wonder if Conway's law is at all responsible for that, in the similarity it is based on; regional trained data which has concept biases which it sends back in response.
Yeah but the pricing is insane, I don't care about SOTA if its not break my bank
tbh companies like anthopic, openai, create custom agents for specific benchmarks
Do you have a source for this? I’m intrigued
https://www-cdn.anthropic.com/07b2a3f9902ee19fe39a36ca638e5a... "we iteratively refine prompting by analyzing failure cases and developing prompts to address them."
The DeepSeek R1 in that list is the old model that's been replaced. Update: Understood.
Yes, and 31.3% is given in the announcement as the performance of the new v3.1, which would put it in sixteenth place.
Depends on the agent. Rank 5 and 15 are claude 4 sonnet, and this stands close to 15th.
It's a hybrid reasoning model. It's good with tool calls and doesn't think too much about everything, but it regularly uses outdated tool formats randomly instead of the standard JSON format. I guess the V3 training set has a lot of those.
Did you try the strict (beta) function calling? https://api-docs.deepseek.com/guides/function_calling
What formats? I thought the very schema of json is what allows these LLMs to enforce structured outputs at the decoder level? I guess you can do it with any format, but why stray from json?
Sometimes it will randomly generate something like this in the body of the text: ``` <tool_call>executeshell <arg_key>command</arg_key> <arg_value>echo "" >> novels/AI_Voodoo_Romance/chapter-1-a-new-dawn.txt</arg_value> </tool_call> ```
or this: ``` <｜toolcallsbegin｜><｜toolcallbegin｜>executeshell<｜toolsep｜>{"command": "pwd && ls -la"}<｜toolcallend｜><｜toolcallsend｜> ```
Prompting it to use the right format doesn't seem to work. Claude, Gemini, GPT5, and GLM 4.5, don't do that. To accomodate DeepSeek, the tiny agent that I'm building will have to support all the weird formats.
It seems behind Qwen3 235B 2507 Reasoning (which I like) and gpt-oss-120B: https://artificialanalysis.ai/models/deepseek-v3-1-reasoning
Pricing: https://openrouter.ai/deepseek/deepseek-chat-v3.1
Those Qwen3 2507 models are the local creme-de-la-creme right now. If you've got any sort of GPU and ~32gb of RAM to play with, the A3B one is great for pair-programming tasks.
I use it on a 24gb gpu Tesla P40. Very happy with the result.
Out of interest, roughly how many tokens per second do you get on that?
Like 4. Definitely single digit. The P40s are slow af
Do you happen to know if it can be run via an eGPU enclosure with f.ex. RTX 5090 inside, under Linux?
I'm considering buying a Linux workstation lately and I want it full AMD. But if I can just plug an NVIDIA card via an eGPU card for self-hosting LLMs then that would be amazing.
I’m running Ollama on 2 eGPUs over Thunderbolt. Works well for me. You’re still dealing with an NVDIA device, of course. The connection type is not going to change that hassle.
Thank you for the validation. As much as I don't like NVIDIA's shenanigans on Linux, having a local LLM is very tempting and I might put my ideological problems to rest over it.
Though I have to ask: why two eGPUs? Is the LLM software smart enough to be able to use any combination of GPUs you point it at?
Yes, Ollama is very plug-and-play when it comes to multi GPU.
llama.cpp probably is too, but I haven't tried it with a bigger model yet.
You would still need drivers and all the stuff difficult with nvidia in linux with a egpu. (Its not nessecarily terrible just suboptimal) Rather just add the second GPU in the Workstation, or just run the llm in your AMD GPU.
Oh, we can run LLMs efficiently with AMD GPUs now? Pretty cool, I haven't been following, thank you.
I've been running LLM models on my Radeon 7600 XT 16GB for past 2-3 months without issues (Windows 11). I've been using llama.cpp only. The only thing from AMD I installed (apart from latest Radeon drivers) is the "AMD HIP SDK" (very straight forward installer). After unzipping (the zip from GitHub releases page must contain hip-radeon in the name) all I do is this:
llama-server.exe -ngl 99 -m Qwen3-14B-Q6_K.gguf
And then connect to llamacpp via browser to localhost:8080 for the WebUI (its basic but does the job, screenshots can be found on Google). You can connect more advanced interfaces to it because llama.cpp actually has OpenAI-compatible API.
Sure, though you'll be bottlenecked by the interconnect speed if you're tiling between system memory and the dGPU memory. That shouldn't be an issue for the 30B model, but would definitely be an issue for the 480B-sized models.
With qwen code?
Unrelated, but it would really be nice to have a chart breaking down Price Per Token Per Second for various model, prompt, and hardware combinations.
Sweet. I wish there guys weren't bound by the idiotic "nationalist" () bans so that they could do their work unrestricted.
Only idiots who are completely drowned in US's dark propaganda would think this is about anything but keeping China down.
Every country acting in its own best interest, US is not unique in this regard
wait until you find out that China also acting the same way toward the rest of the world (surprise pikachu face)
As if the CCP needs help keeping its own people down. Please.