Back to search results
Qwen2.5-Omni-3B · IQ2_M
Intel Arc A770 16GB16GBvLLM v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ2_M) on Intel Arc A770 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
105.24 tok/s
Decode
Decode speed
529.61 tok/s
Prefill
Prefill speed
1.86 s
TTFT
Time to first token
5.38 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_XS Decode 113.09 · Prefill 493.14 ·
- vLLM · IQ2_M (current)Decode 105.24 · Prefill 529.61 ·
- vLLM · IQ4_XS Decode 86.78 · Prefill 278.58 ·
- llama.cpp · Q3_K_S Decode 92.22 · Prefill 373.8 ·
- Strata · IQ2_M Decode 145.2 · Prefill 469.28 ·
Core figures
- Decode (avg)
- 105.24 tok/s
- Prefill (avg)
- 529.61 tok/s
- TTFT (avg)
- 1.86 s
- VRAM (avg)
- 5.38 GB
- MTP acceptance rate
- —
- TTFB
- 0.84 GB
- Power draw
- 182.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- IQ2_M
- Framework
- vLLM
- Version
- v0.54
- Context length
- 2048 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Intel Arc A770 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 5.38 GB
- OS
- Ubuntu 24.04
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 182.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx
105.24 tok/s
Decode
529.61 tok/s
Prefill
1.86 s
TTFT
5.38 GB
VRAM
—
MTP
182.6 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=97 running model_id=60 at IQ2_M