Back to search results
Qwen3.5-27B · IQ3_XS
AMD Strix Halo (Radeon 8060S)Strata v0.41L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-27B (IQ3_XS) on AMD Strix Halo (Radeon 8060S) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
105.76 tok/s
Decode
Decode speed
504.03 tok/s
Prefill
Prefill speed
1.54 s
TTFT
Time to first token
37.25 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 (current)Decode 105.76 · Prefill 504.03 ·
- Strata · Q5_K_M Decode 70.97 · Prefill 388.51 ·
Core figures
- Decode (avg)
- 105.76 tok/s
- Prefill (avg)
- 504.03 tok/s
- TTFT (avg)
- 1.54 s
- VRAM (avg)
- 37.25 GB
- MTP acceptance rate
- 0.68
- TTFB
- 0.85 GB
- Power draw
- 56.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-27B
- Quantization
- IQ3_XS
- Framework
- Strata
- Version
- v0.41
- Context length
- 2048 tokens
- Batch size
- 256
- 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)
- 37.25 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu 6.10
- CUDA
- N/A
- Power draw
- 56.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.41 · Windows 11 23H2 · CUDA N/A · 2048 ctx
105.76 tok/s
Decode
504.03 tok/s
Prefill
1.54 s
TTFT
37.25 GB
VRAM
0.68
MTP
56.6 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=87 running model_id=50 at IQ3_XS