Can the Arc Pro B60 run Qwen3.8-27B-Uncensored-Cyber?
Qwen3.8-27B-Uncensored-Cyber·27.4B·Arc Pro B60·24 GB VRAM
Yes. The Arc Pro B60 runs Qwen3.8-27B-Uncensored-Cyber fully in VRAM at Q4_K_M (about 21 GB of 24 GB), at roughly 15 tokens/s.
- best quant
- Q4_K_M
- needs
- 21 GB
- usable
- 24 GB
- est. speed
- ~15 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Qwen3.8-27B-Uncensored-Cyber page →
Every quantisation of Qwen3.8-27B-Uncensored-Cyber on the Arc Pro B60
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 11 GB | fits | ~28 tok/s |
| Q3_K_M | 16 GB | fits | ~19 tok/s |
| Q4_K_M pick | 21 GB | fits | ~15 tok/s |
| Q5_K_M | 23 GB | tight | ~13 tok/s |
| Q6_K | 26 GB | offload | ~7.8 tok/s |
| Q8_0 | 30 GB | offload | ~3.6 tok/s |
| FP16 / BF16 | 56 GB | too big | — |
Speed is a bandwidth-based estimate for generating text (456 GB/s); prompt processing and long contexts are slower.
Measured speed on the Arc Pro B60
No community reports for this pair yet.
Report your own speed →Run Qwen3.8-27B-Uncensored-Cyber on the Arc Pro B60
Using Q4_K_M, the best fit for Arc Pro B60.
ollama run hf.co/philbert440/Qwen3.8-27B-Uncensored-Cyber-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 philbert440/Qwen3.8-27B-Uncensored-Cyber-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 philbert440/Qwen3.8-27B-Uncensored-Cyber-GGUF:Q4_K_M --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get philbert440/Qwen3.8-27B-Uncensored-Cyber-GGUF@Q4_K_MThen load it from the LM Studio app or with `lms load`.
Vision models that fit the Arc Pro B60 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 27.8B | Q5_K_M | ≈22 GBFits in memory | ~13 tok/s | |
| 27.8B | Q5_K_M | ≈22 GBFits in memory | ~13 tok/s | |
| 25.8BA4B | Q5_K_M | ≈20 GBFits in memory | ~88 tok/s | |
| 27.4B | Q4_K_M | ≈21 GBFits in memory | ~15 tok/s | |
| 27.8B | Q5_K_M | ≈22 GBFits in memory | ~13 tok/s | |
| 29.8B | Q5_K_M | ≈22 GBFits in memory | ~12 tok/s |
Other GPUs that run Qwen3.8-27B-Uncensored-Cyber
Frequently asked questions
- Can the Arc Pro B60 run Qwen3.8-27B-Uncensored-Cyber?
- Yes. The Arc Pro B60 runs Qwen3.8-27B-Uncensored-Cyber fully in VRAM at Q4_K_M (about 21 GB of 24 GB), at roughly 15 tokens/s.
- How fast does Qwen3.8-27B-Uncensored-Cyber run on the Arc Pro B60?
- An estimate from memory bandwidth gives about 15 tokens/s at Q4_K_M.
- Which quantisation of Qwen3.8-27B-Uncensored-Cyber should I use on the Arc Pro B60?
- 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.