Qwen3.5-35B-A3B · IQ2_M
This page aggregates 1 real-world runs of Qwen3.5-35B-A3B (IQ2_M) on Apple M3 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
78.91 tok/s
Decode
Decode speed
300.73 tok/s
Prefill
Prefill speed
2.1 s
TTFT
Time to first token
34.2 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- Ollama · IQ2_M (current)Decode 78.91 · Prefill 300.73 ·
- Strata · IQ2_M Decode 121.51 · Prefill 396.4 ·
Core figures
- Decode (avg)
- 78.91 tok/s
- Prefill (avg)
- 300.73 tok/s
- TTFT (avg)
- 2.1 s
- VRAM (avg)
- 34.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.63 GB
- Power draw
- 89.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-35B-A3B
- Quantization
- IQ2_M
- Framework
- Ollama
- Version
- v0.25
- Context length
- 4096 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)
- 34.2 GB
- OS
- macOS 15.0
- Driver
- Apple M3 Max
- CUDA
- N/A
- Power draw
- 89.1 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 · macOS 15.0 · CUDA N/A · 4096 ctx
78.91 tok/s
Decode
300.73 tok/s
Prefill
2.1 s
TTFT
34.2 GB
VRAM
—
MTP
89.1 W
Power draw
L2 batch seed 2026-10-10: Ollama on hw_id=4 running model_id=15 at IQ2_M