Back to search results
Qwen3.6-35B-A3B · Q3_K_M
Apple M5 Ultra512GBOllama v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (Q3_K_M) on Apple M5 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
206.74 tok/s
Decode
Decode speed
725.54 tok/s
Prefill
Prefill speed
1.64 s
TTFT
Time to first token
52.08 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · Q5_K_S Decode 169.24 · Prefill 662.43 ·
- Ollama · Q3_K_M (current)Decode 206.74 · Prefill 725.54 ·
Core figures
- Decode (avg)
- 206.74 tok/s
- Prefill (avg)
- 725.54 tok/s
- TTFT (avg)
- 1.64 s
- VRAM (avg)
- 52.08 GB
- MTP acceptance rate
- —
- TTFB
- 1.65 GB
- Power draw
- 128.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.6-35B-A3B
- Quantization
- Q3_K_M
- Framework
- Ollama
- Version
- v0.26
- Context length
- 4096 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
- Apple M5 Ultra
- Nominal VRAM
- 512 GB
- Measured VRAM (avg)
- 52.08 GB
- OS
- macOS 26.1
- Power draw
- 128.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · macOS 26.1 · 4096 ctx
206.74 tok/s
Decode
725.54 tok/s
Prefill
1.64 s
TTFT
52.08 GB
VRAM
—
MTP
128.9 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=29 running model_id=47 at Q3_K_M