Back to search results
Qwen3.5-0.8B · IQ3_S
AMD Strix Halo (Radeon 8060S)vLLM v0.24L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ3_S) on AMD Strix Halo (Radeon 8060S) with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
249.57 tok/s
Decode
Decode speed
1,015.71 tok/s
Prefill
Prefill speed
0.19 s
TTFT
Time to first token
3.21 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 · Q3_K_L Decode 205.24 · Prefill 943.68 ·
- llama.cpp · Q3_K_M Decode 229.54 · Prefill 1241.69 ·
- vLLM · IQ3_S (current)Decode 249.57 · Prefill 1015.71 ·
- vLLM · Q3_K_L Decode 238.07 · Prefill 894.22 ·
Core figures
- Decode (avg)
- 249.57 tok/s
- Prefill (avg)
- 1,015.71 tok/s
- TTFT (avg)
- 0.19 s
- VRAM (avg)
- 3.21 GB
- MTP acceptance rate
- —
- TTFB
- 2 GB
- Power draw
- 45.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ3_S
- Framework
- vLLM
- Version
- v0.24
- Context length
- 4096 tokens
- Batch size
- 8
- GPU layers
- 999
- 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)
- 3.21 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 45.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.24 · Windows 11 23H2 · CUDA N/A · 4096 ctx
249.57 tok/s
Decode
1,015.71 tok/s
Prefill
0.19 s
TTFT
3.21 GB
VRAM
—
MTP
45.9 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=87 running model_id=51 at IQ3_S