Back to search results
Qwen2.5-Omni-3B · Q3_K_M
AMD Radeon RX 9070 XT16GBllama.cpp v0.41L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q3_K_M) on AMD Radeon RX 9070 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
169.43 tok/s
Decode
Decode speed
689.96 tok/s
Prefill
Prefill speed
0.36 s
TTFT
Time to first token
6.38 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ3_S Decode 181.8 · Prefill 969.43 ·
- llama.cpp · Q3_K_M (current)Decode 169.43 · Prefill 689.96 ·
- Strata · Q2_K Decode 287.44 · Prefill 1250.58 ·
Core figures
- Decode (avg)
- 169.43 tok/s
- Prefill (avg)
- 689.96 tok/s
- TTFT (avg)
- 0.36 s
- VRAM (avg)
- 6.38 GB
- MTP acceptance rate
- —
- TTFB
- 1.36 GB
- Power draw
- 269.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- Q3_K_M
- Framework
- llama.cpp
- Version
- v0.41
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Radeon RX 9070 XT
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 6.38 GB
- OS
- Ubuntu 24.04
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 269.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.41 · Ubuntu 24.04 · CUDA N/A · 16384 ctx
169.43 tok/s
Decode
689.96 tok/s
Prefill
0.36 s
TTFT
6.38 GB
VRAM
—
MTP
269.6 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=16 running model_id=60 at Q3_K_M