Back to search results
Qwen3-8B · Q5_K_M
Apple M2 Prollama.cpp v0.41L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q5_K_M) on Apple M2 Pro with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
62.75 tok/s
Decode
Decode speed
286.25 tok/s
Prefill
Prefill speed
1.34 s
TTFT
Time to first token
17.72 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 (current)Decode 62.75 · Prefill 286.25 ·
- Strata · IQ2_M Decode 136.65 · Prefill 632.89 ·
Core figures
- Decode (avg)
- 62.75 tok/s
- Prefill (avg)
- 286.25 tok/s
- TTFT (avg)
- 1.34 s
- VRAM (avg)
- 17.72 GB
- MTP acceptance rate
- —
- TTFB
- 0.5 GB
- Power draw
- 52.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q5_K_M
- Framework
- llama.cpp
- Version
- v0.41
- Context length
- 2048 tokens
- Batch size
- 512
- GPU layers
- 28
- 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)
- 17.72 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Pro
- CUDA
- N/A
- Power draw
- 52.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.41 · macOS 15.0 · CUDA N/A · 2048 ctx
62.75 tok/s
Decode
286.25 tok/s
Prefill
1.34 s
TTFT
17.72 GB
VRAM
—
MTP
52.8 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=102 running model_id=53 at Q5_K_M