Can the Arc B580 run DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic?
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic·9.4B·Arc B580·12 GB VRAM
Yes. The Arc B580 runs DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic fully in VRAM at Q8_0 (about 11 GB of 12 GB), at roughly 25 tokens/s.
- best quant
- Q8_0
- needs
- 11 GB
- usable
- 12 GB
- est. speed
- ~25 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic page →
Every quantisation of DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic on the Arc B580
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 5.3 GB | fits | ~81 tok/s |
| Q3_K_M | 6.1 GB | fits | ~55 tok/s |
| Q4_K_M | 7.2 GB | fits | ~44 tok/s |
| Q5_K_M | 8.0 GB | fits | ~37 tok/s |
| Q6_K | 8.9 GB | fits | ~32 tok/s |
| Q8_0 pick | 11 GB | fits | ~25 tok/s |
| FP16 / BF16 | 20 GB | offload | ~3.8 tok/s |
Speed is a bandwidth-based estimate for generating text (456 GB/s); prompt processing and long contexts are slower.
Measured speed on the Arc B580
No community reports for this pair yet.
Report your own speed →Run DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic on the Arc B580
Using Q8_0, the best fit for Arc B580.
ollama run hf.co/mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF:Q8_0Ollama’s ROCm/CUDA builds don’t cover this GPU. Recent Ollama releases use Vulkan when its Vulkan backend and driver are installed (older ones needed OLLAMA_VULKAN=1); llama.cpp or LM Studio with Vulkan are the safer bet.
llama-server -hf mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF:Q8_0Needs a Vulkan build of llama.cpp. Downloads the GGUF on first run.
docker run -d --name llama --device /dev/dri -p 8080:8080 \
-v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
ghcr.io/ggml-org/llama.cpp:server-vulkan \
-hf mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF:Q8_0 --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF@Q8_0Then load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("text-generation", model="xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])Chat models that fit the Arc B580 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 8.2B | Q8_0 | ≈10 GBFits in memory | ~29 tok/s | |
| 8B | Q8_0 | ≈9.8 GBFits in memory | ~29 tok/s | |
| 9.2B | Q6_K | ≈11 GBFits in memory | ~33 tok/s | |
| 8B | Q8_0 | ≈9.8 GBFits in memory | ~29 tok/s | |
| 7.6B | Q8_0 | ≈8.9 GBFits in memory | ~31 tok/s | |
| 9.7B | Q8_0 | ≈11 GBFits in memory | ~24 tok/s |
Other GPUs that run DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
Frequently asked questions
- Can the Arc B580 run DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic?
- Yes. The Arc B580 runs DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic fully in VRAM at Q8_0 (about 11 GB of 12 GB), at roughly 25 tokens/s.
- How fast does DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic run on the Arc B580?
- An estimate from memory bandwidth gives about 25 tokens/s at Q8_0.
- Which quantisation of DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic should I use on the Arc B580?
- Q8_0: the largest one that fits. Expected quality: lossless compared with the full-precision weights.
Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.