Back to search results
Qwen3-8B · IQ2_M
Apple M1 MaxOllama v0.21L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (IQ2_M) on Apple M1 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
105.75 tok/s
Decode
Decode speed
569.54 tok/s
Prefill
Prefill speed
1.9 s
TTFT
Time to first token
10.84 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · IQ2_M (current)Decode 105.75 · Prefill 569.54 ·
- Strata · Q4_K_S Decode 115.1 · Prefill 573.93 ·
Core figures
- Decode (avg)
- 105.75 tok/s
- Prefill (avg)
- 569.54 tok/s
- TTFT (avg)
- 1.9 s
- VRAM (avg)
- 10.84 GB
- MTP acceptance rate
- —
- TTFB
- 0.85 GB
- Power draw
- 40.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- IQ2_M
- Framework
- Ollama
- Version
- v0.21
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M1 Max
- Measured VRAM (avg)
- 10.84 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Max
- CUDA
- N/A
- Power draw
- 40.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.21 · macOS 15.0 · CUDA N/A · 16384 ctx
105.75 tok/s
Decode
569.54 tok/s
Prefill
1.9 s
TTFT
10.84 GB
VRAM
—
MTP
40.6 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=101 running model_id=53 at IQ2_M