Back to search results
Qwen2.5-Omni-3B · IQ2_M
NVIDIA DGX Spark128GBOllama v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ2_M) on NVIDIA DGX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
292.67 tok/s
Decode
Decode speed
1,302.54 tok/s
Prefill
Prefill speed
0.89 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
- vLLM · Q3_K_M Decode 258.63 · Prefill 1322.45 ·
- vLLM · Q5_K_M Decode 183.75 · Prefill 675.77 ·
- Ollama · IQ2_M (current)Decode 292.67 · Prefill 1302.54 ·
- Ollama · IQ4_XS Decode 218.18 · Prefill 903.32 ·
Core figures
- Decode (avg)
- 292.67 tok/s
- Prefill (avg)
- 1,302.54 tok/s
- TTFT (avg)
- 0.89 s
- VRAM (avg)
- 5.38 GB
- MTP acceptance rate
- —
- TTFB
- 2.34 GB
- Power draw
- 226.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- IQ2_M
- Framework
- Ollama
- Version
- v0.43
- Context length
- 2048 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
- NVIDIA DGX Spark
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 5.38 GB
- OS
- Ubuntu 22.04
- Driver
- 570.86
- CUDA
- 12.6
- Power draw
- 226.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · Ubuntu 22.04 · CUDA 12.6 · 2048 ctx
292.67 tok/s
Decode
1,302.54 tok/s
Prefill
0.89 s
TTFT
5.38 GB
VRAM
—
MTP
226.8 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=54 running model_id=60 at IQ2_M