Qwen3.6-27B · vLLM · NVFP4 · conc 8
status: done
Configuration
| Model | Qwen/Qwen3.6-27B |
|---|---|
| Company | Alibaba |
| Family | Qwen |
| Parameters | 27B (dense) |
| Engine | vLLM |
| Quant / precision | NVFP4 |
| Why this quant | conc-8 base (non-spec) point of the Qwen3.6-27B NVFP4 sweep — matched no-spec baseline for the MTP conc-8 row (EXPERIMENTS.md |
| Download | unsloth/Qwen3.6-27B-NVFP4 |
| Context window | 65536 |
| Input modalities | text, image, video (served text-only here) |
Measured results
| Prefill tok/s | 68.25 |
|---|---|
| Decode tok/s | 67.06 |
| Peak memory (GB) | 107.09 (system MemAvailable delta (10s sampling) — vLLM static KV reservation (util 0.85)) |
| Completed | 2026-07-01 22:32 +0800 |
Full run command
# conc-8 base (no spec). Same recipe as the published conc-32 base — only --max-num-seqs differs.
scripts/bench-vllm-serving.sh unsloth/Qwen3.6-27B-NVFP4 65536 8 1000 600 256 \
--trust-remote-code --dtype bfloat16
Notes
conc-8 base (no-spec) point of the Qwen3.6-27B NVFP4 sweep — matched baseline for the MTP conc-8 row (EXPERIMENTS.md #4/#14).
- Result (conc 8): prefill 68.25 / decode 67.06 tok/s aggregate; 0 errors; peak mem 107.1 GB.
- Scaling starts to bend by conc-8 (9.33 → 18.11 → 35.54 → 67.06 at c1/2/4/8 ≈ ×1.94/×1.96/×1.89) — still strong but no longer perfectly linear as the dense 27B begins to fill the compute.
- MTP speedup at conc-8: MTP
-mtp-c8109.05 vs this base 67.06 = +62.6% — the dense model keeps a large MTP win at moderate batch (vs the 35B-A3B MoE’s ~+20% at c8), because a dense target has less spare compute to lose to draft overhead. MTP accepts ~71% / accept-len ~3.1. - Sweep siblings (base):
-c1·-c2·-c4·-c16·c32(main).