Can the Arc A580 run DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic?
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic·9.4B·Arc A580·8 GB VRAM
Yes. The Arc A580 runs DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic fully in VRAM at Q4_K_M (about 7.2 GB of 8.0 GB), at roughly 49 tokens/s.
- best quant
- Q4_K_M
- needs
- 7.2 GB
- usable
- 8.0 GB
- est. speed
- ~49 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 A580
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 5.3 GB | fits | ~91 tok/s |
| Q3_K_M | 6.1 GB | fits | ~61 tok/s |
| Q4_K_M pick | 7.2 GB | fits | ~49 tok/s |
| Q5_K_M | 8.0 GB | tight | ~42 tok/s |
| Q6_K | 8.9 GB | offload | ~21 tok/s |
| Q8_0 | 11 GB | offload | ~9.1 tok/s |
| FP16 / BF16 | 20 GB | offload | ~2.7 tok/s |
Speed is a bandwidth-based estimate for generating text (512 GB/s); prompt processing and long contexts are slower.
Measured speed on the Arc A580
No community reports for this pair yet.
Report your own speed →Run DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic on the Arc A580
Using Q4_K_M, the best fit for Arc A580.
ollama run hf.co/mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF:Q4_K_MOllama’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:Q4_K_MNeeds 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:Q4_K_M --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@Q4_K_MThen 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 A580 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 8.2B | Q5_K_M | ≈7.3 GBFits in memory | ~48 tok/s | |
| 8B | Q5_K_M | ≈7.1 GBFits in memory | ~49 tok/s | |
| 7.6B | Q6_K | ≈7.0 GBFits in memory | ~45 tok/s | |
| 8B | Q5_K_M | ≈7.1 GBFits in memory | ~49 tok/s | |
| 9.7B | Q4_K_M | ≈7.3 GBFits in memory | ~48 tok/s | |
| 8.8B | Q4_K_M | ≈7.0 GBFits in memory | ~53 tok/s |
Other GPUs that run DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
Frequently asked questions
- Can the Arc A580 run DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic?
- Yes. The Arc A580 runs DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic fully in VRAM at Q4_K_M (about 7.2 GB of 8.0 GB), at roughly 49 tokens/s.
- How fast does DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic run on the Arc A580?
- An estimate from memory bandwidth gives about 49 tokens/s at Q4_K_M.
- Which quantisation of DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic should I use on the Arc A580?
- Q4_K_M: the largest one that fits. Expected quality: small loss 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.