Back to search results
Qwen3.5-0.8B · Q2_K
2x AMD Strix HaloStrata v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q2_K) on 2x AMD Strix Halo with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
284.75 tok/s
Decode
Decode speed
1,118.17 tok/s
Prefill
Prefill speed
0.66 s
TTFT
Time to first token
3.02 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · FP16 Decode 163.9 · Prefill 573.99 ·
- vLLM · IQ3_XS Decode 352.1 · Prefill 1673.75 ·
- Strata · Q2_K (current)Decode 284.75 · Prefill 1118.17 ·
- Strata · Q5_K_S Decode 358.45 · Prefill 1286.06 ·
Core figures
- Decode (avg)
- 284.75 tok/s
- Prefill (avg)
- 1,118.17 tok/s
- TTFT (avg)
- 0.66 s
- VRAM (avg)
- 3.02 GB
- MTP acceptance rate
- 0.65
- TTFB
- 2.28 GB
- Power draw
- 66.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q2_K
- Framework
- Strata
- Version
- v0.31
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 15
- 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)
- 3.02 GB
- OS
- Ubuntu 24.04
- Driver
- amdgpu 6.10
- CUDA
- N/A
- Power draw
- 66.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · Ubuntu 24.04 · CUDA N/A · 16384 ctx
284.75 tok/s
Decode
1,118.17 tok/s
Prefill
0.66 s
TTFT
3.02 GB
VRAM
0.65
MTP
66.2 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=88 running model_id=51 at Q2_K