Qwen3.8 27B Escha-W2
NVIDIA RTX 4080 Super · SGLang · 98,304 ctx
- generation:
- 59.0 tokens/s
- quant:
- 2.469 bpw
- kv:
- FP8 E4M3
codingagenticlong-context
User reports Qwen3.8-27B-Escha-W2 at about 59 t/s short context and about 50.5 t/s at 60K context on a 16 GB RTX 4080 Super, pushed to 98K context. Setup is Escha's SGLang build with a 2.469 bpw quant, FP8 KV cache and BF16 SSM state. MTP4 gave about 67.7 t/s at 64K context, but the user chose no speculation for maximum context. The user finds quality surprisingly good despite the aggressive quant.