Can the Arc A380 run Qwen3.8-4B-Distill?
Qwen3.8-4B-Distill·4.7B·Arc A380·6 GB VRAM
Yes. The Arc A380 runs Qwen3.8-4B-Distill fully in VRAM at Q6_K (about 5.0 GB of 6.0 GB), at roughly 27 tokens/s.
- best quant
- Q6_K
- needs
- 5.0 GB
- usable
- 6.0 GB
- est. speed
- ~27 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Qwen3.8-4B-Distill page →
Every quantisation of Qwen3.8-4B-Distill on the Arc A380
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 3.4 GB | fits | ~67 tok/s |
| Q3_K_M | 3.8 GB | fits | ~45 tok/s |
| Q4_K_M | 4.2 GB | fits | ~36 tok/s |
| Q5_K_M | 4.6 GB | fits | ~31 tok/s |
| Q6_K pick | 5.0 GB | fits | ~27 tok/s |
| Q8_0 | 6.0 GB | tight | ~21 tok/s |
| FP16 / BF16 | 10.0 GB | offload | ~6 tok/s |
Speed is a bandwidth-based estimate for generating text (186 GB/s); prompt processing and long contexts are slower.
Measured speed on the Arc A380
No community reports for this pair yet.
Report your own speed →Run Qwen3.8-4B-Distill on the Arc A380
Using Q6_K, the best fit for Arc A380.
ollama run hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q6_KOllama’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 empero-ai/Qwen3.8-4B-Distill-GGUF:Q6_KNeeds 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 empero-ai/Qwen3.8-4B-Distill-GGUF:Q6_K --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get empero-ai/Qwen3.8-4B-Distill-GGUF@Q6_KThen load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("text-generation", model="empero-ai/Qwen3.8-4B-Distill", 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 A380 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 4B | Q6_K | ≈4.9 GBFits in memory | ~31 tok/s | |
| 4B | Q6_K | ≈4.9 GBFits in memory | ~31 tok/s | |
| 4.1B | Q6_K | ≈4.9 GBFits in memory | ~30 tok/s | |
| 3.8B | Q8_0 | ≈5.5 GBFits in memory | ~25 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~30 tok/s | |
| 4.1B | Q6_K | ≈4.9 GBFits in memory | ~30 tok/s |
Other GPUs that run Qwen3.8-4B-Distill
Frequently asked questions
- Can the Arc A380 run Qwen3.8-4B-Distill?
- Yes. The Arc A380 runs Qwen3.8-4B-Distill fully in VRAM at Q6_K (about 5.0 GB of 6.0 GB), at roughly 27 tokens/s.
- How fast does Qwen3.8-4B-Distill run on the Arc A380?
- An estimate from memory bandwidth gives about 27 tokens/s at Q6_K.
- Which quantisation of Qwen3.8-4B-Distill should I use on the Arc A380?
- Q6_K: the largest one that fits. Expected quality: near-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.