Back to search results
Qwen2.5-Omni-3B · IQ4_XS
NVIDIA RTX 509032GBllama.cpp v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ4_XS) on NVIDIA RTX 5090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
375.39 tok/s
Decode
Decode speed
1,839.32 tok/s
Prefill
Prefill speed
1.93 s
TTFT
Time to first token
6.76 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 · IQ4_XS (current)Decode 375.39 · Prefill 1839.32 ·
- llama.cpp · Q6_K Decode 277.82 · Prefill 934.6 ·
- Strata · FP16 Decode 238.76 · Prefill 798.02 ·
- Strata · IQ3_S Decode 359.64 · Prefill 1323.17 ·
- llama.cpp · Q8_0 Decode 436.8 · Prefill 3276 ·
- llama.cpp · Q5_K_M Decode 635.3 · Prefill 4764.8 ·
- llama.cpp · Q4_K_M Decode 776.5 · Prefill 5823.8 ·
Core figures
- Decode (avg)
- 375.39 tok/s
- Prefill (avg)
- 1,839.32 tok/s
- TTFT (avg)
- 1.93 s
- VRAM (avg)
- 6.76 GB
- MTP acceptance rate
- —
- TTFB
- 3 GB
- Power draw
- 279.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- IQ4_XS
- Framework
- llama.cpp
- Version
- v0.40
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 6.76 GB
- OS
- macOS 15.0
- Driver
- 555.85
- CUDA
- 12.4
- Power draw
- 279.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · macOS 15.0 · CUDA 12.4 · 32768 ctx
375.39 tok/s
Decode
1,839.32 tok/s
Prefill
1.93 s
TTFT
6.76 GB
VRAM
—
MTP
279.1 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=13 running model_id=60 at IQ4_XS