Qwen3.6-27B · Q4_K_S
This page aggregates 1 real-world runs of Qwen3.6-27B (Q4_K_S) on Apple M5 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
81.06 tok/s
Decode
Decode speed
387.21 tok/s
Prefill
Prefill speed
1.78 s
TTFT
Time to first token
46.33 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · IQ3_XS Decode 91.11 · Prefill 454.84 ·
- llama.cpp · Q4_K_S (current)Decode 81.06 · Prefill 387.21 ·
- Ollama · IQ3_S Decode 85.88 · Prefill 388.53 ·
- Ollama · Q6_K Decode 53.29 · Prefill 218.93 ·
Core figures
- Decode (avg)
- 81.06 tok/s
- Prefill (avg)
- 387.21 tok/s
- TTFT (avg)
- 1.78 s
- VRAM (avg)
- 46.33 GB
- MTP acceptance rate
- —
- TTFB
- 0.65 GB
- Power draw
- 91.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.6-27B
- Quantization
- Q4_K_S
- Framework
- llama.cpp
- Version
- v0.33
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Ultra
- Nominal VRAM
- 512 GB
- Measured VRAM (avg)
- 46.33 GB
- OS
- macOS 26.1
- Power draw
- 91.4 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
v0.33 · macOS 26.1 · 32768 ctx
81.06 tok/s
Decode
387.21 tok/s
Prefill
1.78 s
TTFT
46.33 GB
VRAM
—
MTP
91.4 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=29 running model_id=6 at Q4_K_S