Back to search results
Qwen2.5-Omni-3B · IQ1_S
Apple M5 Max128GBllama.cpp v0.46L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ1_S) on Apple M5 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
289.86 tok/s
Decode
Decode speed
1,338.5 tok/s
Prefill
Prefill speed
1.76 s
TTFT
Time to first token
4.75 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ3_S Decode 341.31 · Prefill 1584.99 ·
- llama.cpp · Q6_K Decode 221.16 · Prefill 1117.52 ·
- Strata · Q8_0 Decode 241.28 · Prefill 991.2 ·
- llama.cpp · IQ1_S (current)Decode 289.86 · Prefill 1338.5 ·
Core figures
- Decode (avg)
- 289.86 tok/s
- Prefill (avg)
- 1,338.5 tok/s
- TTFT (avg)
- 1.76 s
- VRAM (avg)
- 4.75 GB
- MTP acceptance rate
- —
- TTFB
- 2.32 GB
- Power draw
- 56.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- IQ1_S
- Framework
- llama.cpp
- Version
- v0.46
- 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 M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 4.75 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Max
- CUDA
- N/A
- Power draw
- 56.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.46 · macOS 15.0 · CUDA N/A · 16384 ctx
289.86 tok/s
Decode
1,338.5 tok/s
Prefill
1.76 s
TTFT
4.75 GB
VRAM
—
MTP
56.1 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=28 running model_id=60 at IQ1_S