Qwen3.8 27B
NVIDIA DGX Spark · ExLlamaV3 · 262,144 ctx
- generation:
- 47.5 tokens/s
- quant:
- EXL3 3.5bpw (EXL3)
- kv:
- nvfp4
codingtool-use
User reports Qwen3.8-27B at 47.5 tok/s on a DGX Spark (GB10). Setup is the exllamav3 fork with EXL3 3.5bpw weights, nvfp4 KV cache, and DFlash2 speculative decoding (EXL3 5.0bpw draft, 1.4 GB). The 47.5 tok/s figure is HumanEval-class decode at T=0.6 with acceptance 4.43 tokens/step; the kit also cites ~30 tok/s with MTP and ~34.5 tok/s with DFlash2 at 24 GB, and ~16.7 tok/s aggregate across 8 concurrent requests.