Back to search results
Qwen2.5-0.5B-Instruct · Q4_K_M
Apple M1 Prollama.cpp v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q4_K_M) on Apple M1 Pro with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
190.83 tok/s
Decode
Decode speed
796.91 tok/s
Prefill
Prefill speed
2.05 s
TTFT
Time to first token
2.96 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 · Q4_K_M (current)Decode 190.83 · Prefill 796.91 ·
- vLLM · Q4_K_M Decode 203.19 · Prefill 994.69 ·
Core figures
- Decode (avg)
- 190.83 tok/s
- Prefill (avg)
- 796.91 tok/s
- TTFT (avg)
- 2.05 s
- VRAM (avg)
- 2.96 GB
- MTP acceptance rate
- —
- TTFB
- 1.53 GB
- Power draw
- 73.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- Q4_K_M
- Framework
- llama.cpp
- Version
- v0.26
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M1 Pro
- Measured VRAM (avg)
- 2.96 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Pro
- CUDA
- N/A
- Power draw
- 73.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · macOS 15.0 · CUDA N/A · 2048 ctx
190.83 tok/s
Decode
796.91 tok/s
Prefill
2.05 s
TTFT
2.96 GB
VRAM
—
MTP
73.6 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=100 running model_id=59 at Q4_K_M