Back to search results
Qwen2.5-0.5B-Instruct · IQ2_M
Apple M1llama.cpp v0.42L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ2_M) on Apple M1 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
189.83 tok/s
Decode
Decode speed
1,001.05 tok/s
Prefill
Prefill speed
1.48 s
TTFT
Time to first token
2.65 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 · IQ2_M (current)Decode 189.83 · Prefill 1001.05 ·
- llama.cpp · Q2_K Decode 189.43 · Prefill 860.24 ·
- vLLM · Q3_K_S Decode 170.33 · Prefill 911.66 ·
- vLLM · Q4_K_M Decode 143.97 · Prefill 610.72 ·
Core figures
- Decode (avg)
- 189.83 tok/s
- Prefill (avg)
- 1,001.05 tok/s
- TTFT (avg)
- 1.48 s
- VRAM (avg)
- 2.65 GB
- MTP acceptance rate
- —
- TTFB
- 1.52 GB
- Power draw
- 42.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- IQ2_M
- Framework
- llama.cpp
- Version
- v0.42
- Context length
- 16384 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 M1
- Measured VRAM (avg)
- 2.65 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 42.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.42 · macOS 15.0 · CUDA N/A · 16384 ctx
189.83 tok/s
Decode
1,001.05 tok/s
Prefill
1.48 s
TTFT
2.65 GB
VRAM
—
MTP
42.2 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=99 running model_id=59 at IQ2_M