Back to search results
Qwen3.5-0.8B · Q3_K_M
Apple M3 Max36GBOllama v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q3_K_M) on Apple M3 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
286.62 tok/s
Decode
Decode speed
1,285.71 tok/s
Prefill
Prefill speed
1.04 s
TTFT
Time to first token
3.24 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ2_XS Decode 369.47 · Prefill 2026.25 ·
- llama.cpp · IQ3_XS Decode 313.86 · Prefill 1064.12 ·
- Ollama · Q3_K_M (current)Decode 286.62 · Prefill 1285.71 ·
- Strata · Q8_0 Decode 237.48 · Prefill 1069.27 ·
Core figures
- Decode (avg)
- 286.62 tok/s
- Prefill (avg)
- 1,285.71 tok/s
- TTFT (avg)
- 1.04 s
- VRAM (avg)
- 3.24 GB
- MTP acceptance rate
- —
- TTFB
- 2.29 GB
- Power draw
- 81.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q3_K_M
- Framework
- Ollama
- Version
- v0.33
- Context length
- 32768 tokens
- Batch size
- 512
- 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 M3 Max
- Nominal VRAM
- 36 GB
- Measured VRAM (avg)
- 3.24 GB
- OS
- macOS 15.0
- Driver
- Apple M3 Max
- CUDA
- N/A
- Power draw
- 81.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · macOS 15.0 · CUDA N/A · 32768 ctx
286.62 tok/s
Decode
1,285.71 tok/s
Prefill
1.04 s
TTFT
3.24 GB
VRAM
—
MTP
81.1 W
Power draw
L2 batch seed 2026-10-10: Ollama on hw_id=4 running model_id=51 at Q3_K_M