Back to search results
Qwen3.5-27B · Q5_K_M
AMD Strix Halo (Radeon 8060S)Strata v0.42L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-27B (Q5_K_M) on AMD Strix Halo (Radeon 8060S) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
70.97 tok/s
Decode
Decode speed
388.51 tok/s
Prefill
Prefill speed
1.91 s
TTFT
Time to first token
54.83 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · IQ3_S Decode 74.72 · Prefill 343.92 ·
- Strata · IQ3_XS Decode 105.76 · Prefill 504.03 ·
- Strata · Q5_K_M (current)Decode 70.97 · Prefill 388.51 ·
Core figures
- Decode (avg)
- 70.97 tok/s
- Prefill (avg)
- 388.51 tok/s
- TTFT (avg)
- 1.91 s
- VRAM (avg)
- 54.83 GB
- MTP acceptance rate
- 0.54
- TTFB
- 0.57 GB
- Power draw
- 91.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-27B
- Quantization
- Q5_K_M
- Framework
- Strata
- Version
- v0.42
- Context length
- 2048 tokens
- Batch size
- 512
- GPU layers
- 8
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Strix Halo (Radeon 8060S)
- Measured VRAM (avg)
- 54.83 GB
- OS
- Ubuntu 24.04
- Driver
- amdgpu 6.11
- CUDA
- N/A
- Power draw
- 91.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.42 · Ubuntu 24.04 · CUDA N/A · 2048 ctx
70.97 tok/s
Decode
388.51 tok/s
Prefill
1.91 s
TTFT
54.83 GB
VRAM
0.54
MTP
91.2 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=87 running model_id=50 at Q5_K_M