Back to search results
Qwen3-8B · IQ2_M
Apple M2 ProStrata v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (IQ2_M) on Apple M2 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
136.65 tok/s
Decode
Decode speed
632.89 tok/s
Prefill
Prefill speed
0.15 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
- llama.cpp · Q5_K_M Decode 62.75 · Prefill 286.25 ·
- Strata · IQ2_M (current)Decode 136.65 · Prefill 632.89 ·
Core figures
- Decode (avg)
- 136.65 tok/s
- Prefill (avg)
- 632.89 tok/s
- TTFT (avg)
- 0.15 s
- VRAM (avg)
- 10.84 GB
- MTP acceptance rate
- 0.51
- TTFB
- 1.09 GB
- Power draw
- 60.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- IQ2_M
- Framework
- Strata
- Version
- v0.51
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 12
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Pro
- Measured VRAM (avg)
- 10.84 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Pro
- CUDA
- N/A
- Power draw
- 60.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · macOS 15.0 · CUDA N/A · 2048 ctx
136.65 tok/s
Decode
632.89 tok/s
Prefill
0.15 s
TTFT
10.84 GB
VRAM
0.51
MTP
60.3 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=102 running model_id=53 at IQ2_M