Back to search results
Qwen2.5-Omni-3B · IQ3_XS
Apple M1Ollama v0.21L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ3_XS) on Apple M1 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
74.16 tok/s
Decode
Decode speed
283.84 tok/s
Prefill
Prefill speed
1.83 s
TTFT
Time to first token
6.01 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · IQ3_XS (current)Decode 74.16 · Prefill 283.84 ·
- Ollama · Q6_K Decode 48.37 · Prefill 198.04 ·
- Strata · Q3_K_M Decode 114.61 · Prefill 400.65 ·
Core figures
- Decode (avg)
- 74.16 tok/s
- Prefill (avg)
- 283.84 tok/s
- TTFT (avg)
- 1.83 s
- VRAM (avg)
- 6.01 GB
- MTP acceptance rate
- —
- TTFB
- 0.59 GB
- Power draw
- 65.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- IQ3_XS
- Framework
- Ollama
- Version
- v0.21
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M1
- Measured VRAM (avg)
- 6.01 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 65.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.21 · macOS 15.0 · CUDA N/A · 32768 ctx
74.16 tok/s
Decode
283.84 tok/s
Prefill
1.83 s
TTFT
6.01 GB
VRAM
—
MTP
65.5 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=99 running model_id=60 at IQ3_XS