Qwen3.6-27B · IQ1_S
This page aggregates 1 real-world runs of Qwen3.6-27B (IQ1_S) on Apple M5 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
83.43 tok/s
Decode
Decode speed
309.76 tok/s
Prefill
Prefill speed
0.15 s
TTFT
Time to first token
25.91 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · IQ1_S (current)Decode 83.43 · Prefill 309.76 ·
- Ollama · IQ4_XS Decode 48.58 · Prefill 245.06 ·
Core figures
- Decode (avg)
- 83.43 tok/s
- Prefill (avg)
- 309.76 tok/s
- TTFT (avg)
- 0.15 s
- VRAM (avg)
- 25.91 GB
- MTP acceptance rate
- —
- TTFB
- 0.67 GB
- Power draw
- 68.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.6-27B
- Quantization
- IQ1_S
- Framework
- llama.cpp
- Version
- v0.29
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 20
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 25.91 GB
- OS
- macOS 26.1
- Power draw
- 68.6 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
v0.29 · macOS 26.1 · 32768 ctx
83.43 tok/s
Decode
309.76 tok/s
Prefill
0.15 s
TTFT
25.91 GB
VRAM
—
MTP
68.6 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=28 running model_id=6 at IQ1_S