Qwen3.6-27B · IQ1_S
This page aggregates 1 real-world runs of Qwen3.6-27B (IQ1_S) on NVIDIA RTX 3090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
96.12 tok/s
Decode
Decode speed
373.79 tok/s
Prefill
Prefill speed
0.28 s
TTFT
Time to first token
22.8 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- vLLM · IQ1_S (current)Decode 96.12 · Prefill 373.79 ·
- Ollama · IQ1_S Decode 76.57 · Prefill 351.59 ·
- llama.cpp · Q4_K_M Decode 57.02 · Prefill 1299.01 ·
- llama.cpp · UD-Q3_K_XL Decode 36.67 · Prefill 39.44 ·
- llama.cpp · Q5_K_S Decode 46.57 · Prefill 1201.22 ·
Core figures
- Decode (avg)
- 96.12 tok/s
- Prefill (avg)
- 373.79 tok/s
- TTFT (avg)
- 0.28 s
- VRAM (avg)
- 22.8 GB
- MTP acceptance rate
- —
- TTFB
- 0.77 GB
- Power draw
- 322.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.6-27B
- Quantization
- IQ1_S
- Framework
- vLLM
- Version
- v0.25
- Context length
- 4096 tokens
- Batch size
- 8
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 22.8 GB
- OS
- Windows 11 24H2
- Driver
- 570.86
- CUDA
- 12.4
- Power draw
- 322.5 W
Get started
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Sources & evidence
1 measured records in total, each traceable to its original source
v0.25 · Windows 11 24H2 · CUDA 12.4 · 4096 ctx
96.12 tok/s
Decode
373.79 tok/s
Prefill
0.28 s
TTFT
22.8 GB
VRAM
—
MTP
322.5 W
Power draw
L2 batch seed 2026-10-19: vLLM on hw_id=2 running model_id=6 at IQ1_S