Qwen3.6-27B · IQ1_S
This page aggregates 1 real-world runs of Qwen3.6-27B (IQ1_S) on NVIDIA RTX 5090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
273.05 tok/s
Decode
Decode speed
882.7 tok/s
Prefill
Prefill speed
2.42 s
TTFT
Time to first token
25.91 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ1_S (current)Decode 273.05 · Prefill 882.7 ·
Core figures
- Decode (avg)
- 273.05 tok/s
- Prefill (avg)
- 882.7 tok/s
- TTFT (avg)
- 2.42 s
- VRAM (avg)
- 25.91 GB
- MTP acceptance rate
- —
- TTFB
- 2.18 GB
- Power draw
- 432 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.6-27B
- Quantization
- IQ1_S
- Framework
- llama.cpp
- Version
- v0.25
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 25.91 GB
- OS
- Windows 11 23H2
- Driver
- 565.57
- CUDA
- 12.4
- Power draw
- 432 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 23H2 · CUDA 12.4 · 8192 ctx
273.05 tok/s
Decode
882.7 tok/s
Prefill
2.42 s
TTFT
25.91 GB
VRAM
—
MTP
432 W
Power draw
L2 batch seed 2026-10-10: llama.cpp on hw_id=13 running model_id=6 at IQ1_S