llamaperf

Muse 30B Glimmer

on Unknown GPU · ExLlamaV3 · 100,000 ctx

Tone: positive
Sep 8, 2026
Throughput
30.0 t/s gen
Quant
EXL3-SC 3.00bpw H4 (EXL3)
KV cache
Q8
VRAM reported
12 GB

Summary

User reports Qwen 3.8 27B at SC2.20bpw H3. User prefers Unsloth UD_Q4_K_XL for coding.