Can the Arc Pro B60 run Qwen3.8 27B?
Yes. Qwen3.8 27B fits the Arc Pro B60's 24 GB at Q4_K_M (about 17.8 GB needed), running at an estimated 16 tok/s. There's room for up to Q5_K_M if you want higher quality.
Every quantization
Qwen3.8 27B (27.8B) on 24 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 16 GB | 17.8 GB | Fits | ~16 tok/s |
| Q5_K_M | 20 GB | 21.8 GB | Tight | ~13 tok/s |
| Q8_0 | 30 GB | 31.8 GB | Too big | - |
| FP16 | 56 GB | 57.8 GB | Too big | - |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the Arc Pro B60's 456 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
Compare
Same model, other hardware - and other models on this card
Qwen3.8 27B on other hardware
- RTX 5090~64 tok/s
- RTX 5090 D~64 tok/s
- RTX 6000D~56 tok/s
- RTX 4090~39 tok/s
- RTX 3090~34 tok/s
- Radeon RX 7900 XTX~34 tok/s
- MacBook Pro 16" M4 Max~20 tok/s
- DGX Spark (GB10)~9.8 tok/s
Also runs on the Arc Pro B60
- GLM-4.7-Flash~101 tok/s
- Qwen3-30B-A3B-Instruct-2507~99 tok/s
- Qwen3.6 27B~16 tok/s
- Gemma 4 26B A4B~77 tok/s
- gpt-oss-20b~87 tok/s
- Qwen2.5-Coder-14B-Instruct~29 tok/s
- Qwen3 14B~33 tok/s
- Phi-4~31 tok/s
Frequently asked
Quick answers
Can the Arc Pro B60 run Qwen3.8 27B?
Yes. Qwen3.8 27B fits the Arc Pro B60's 24 GB at Q4_K_M (about 17.8 GB needed), running at an estimated 16 tok/s. There's room for up to Q5_K_M if you want higher quality.
How much VRAM does Qwen3.8 27B need?
About 16 GB of weights at Q4_K_M, 30 GB at Q8_0 and 56 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Qwen3.8 27B on the Arc Pro B60?
Roughly 16 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the Arc Pro B60's 456 GB/s memory bandwidth.