Back to search results
Qwen2.5-Omni-3B · Q4_K_M
NVIDIA RTX 407012GBOllama v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q4_K_M) on NVIDIA RTX 4070 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
96.06 tok/s
Decode
Decode speed
324.01 tok/s
Prefill
Prefill speed
1.6 s
TTFT
Time to first token
7.27 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Ollama · Q4_K_M (current)Decode 96.06 · Prefill 324.01 ·
- Ollama · Q5_K_M Decode 86.83 · Prefill 374.83 ·
Core figures
- Decode (avg)
- 96.06 tok/s
- Prefill (avg)
- 324.01 tok/s
- TTFT (avg)
- 1.6 s
- VRAM (avg)
- 7.27 GB
- MTP acceptance rate
- —
- TTFB
- 0.77 GB
- Power draw
- 209.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- Q4_K_M
- Framework
- Ollama
- Version
- v0.51
- Context length
- 4096 tokens
- Batch size
- 512
- 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
- NVIDIA RTX 4070
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 7.27 GB
- OS
- macOS 15.0
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 209.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · macOS 15.0 · CUDA 12.6 · 4096 ctx
96.06 tok/s
Decode
324.01 tok/s
Prefill
1.6 s
TTFT
7.27 GB
VRAM
—
MTP
209.3 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=45 running model_id=60 at Q4_K_M