Back to search results
Qwen2.5-Omni-3B · Q4_K_M
AMD Ryzen AI Max+ 395128GBStrata v0.36L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q4_K_M) on AMD Ryzen AI Max+ 395 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
218.64 tok/s
Decode
Decode speed
754.88 tok/s
Prefill
Prefill speed
1.97 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
2 days ago
Last verified
Performance
- vLLM · IQ3_S Decode 201.15 · Prefill 1047.45 ·
- vLLM · Q2_K Decode 204.49 · Prefill 918.23 ·
- Strata · Q4_K_M (current)Decode 218.64 · Prefill 754.88 ·
- Strata · Q8_0 Decode 147.88 · Prefill 774.09 ·
- llama.cpp · Q4_K_S Decode 153.58 · Prefill 827.06 ·
- llama.cpp · Q8_0 Decode 98.01 · Prefill 478.15 ·
- Ollama · Q3_K_S Decode 173.92 · Prefill 636.41 ·
- Ollama · Q4_K_S Decode 150.76 · Prefill 704.53 ·
Core figures
- Decode (avg)
- 218.64 tok/s
- Prefill (avg)
- 754.88 tok/s
- TTFT (avg)
- 1.97 s
- VRAM (avg)
- 7.27 GB
- MTP acceptance rate
- 0.6
- TTFB
- 1.75 GB
- Power draw
- 88.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- Q4_K_M
- Framework
- Strata
- Version
- v0.36
- Context length
- 4096 tokens
- Batch size
- 1024
- GPU layers
- 15
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Ryzen AI Max+ 395
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 7.27 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- N/A
- Power draw
- 88.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.36 · Ubuntu 24.04 · CUDA N/A · 4096 ctx
218.64 tok/s
Decode
754.88 tok/s
Prefill
1.97 s
TTFT
7.27 GB
VRAM
0.6
MTP
88.9 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=24 running model_id=60 at Q4_K_M