syv-ai / qwen38-27b-rtx3090View on GitHub
Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks
1,129Sep 4, 2026Updated this week

Alternatives and similar repositories for qwen38-27b-rtx3090

Users that are interested in qwen38-27b-rtx3090 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?