Back to search results
Qwen3.5-4B · Q5_K_M
2x AMD Strix HaloStrata v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q5_K_M) on 2x AMD Strix Halo with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
206.52 tok/s
Decode
Decode speed
718.15 tok/s
Prefill
Prefill speed
1.03 s
TTFT
Time to first token
9.91 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 · FP16 Decode 94.9 · Prefill 326.17 ·
- Strata · Q5_K_M (current)Decode 206.52 · Prefill 718.15 ·
Core figures
- Decode (avg)
- 206.52 tok/s
- Prefill (avg)
- 718.15 tok/s
- TTFT (avg)
- 1.03 s
- VRAM (avg)
- 9.91 GB
- MTP acceptance rate
- 0.6
- TTFB
- 1.65 GB
- Power draw
- 61.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q5_K_M
- Framework
- Strata
- Version
- v0.31
- Context length
- 2048 tokens
- Batch size
- 1024
- GPU layers
- 12
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- 2x AMD Strix Halo
- Measured VRAM (avg)
- 9.91 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- N/A
- Power draw
- 61.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · Windows 11 23H2 · CUDA N/A · 2048 ctx
206.52 tok/s
Decode
718.15 tok/s
Prefill
1.03 s
TTFT
9.91 GB
VRAM
0.6
MTP
61.8 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=88 running model_id=48 at Q5_K_M