Back to search results
Qwen3.5-0.8B · Q3_K_M
AMD Strix Halo (Radeon 8060S)llama.cpp v0.52L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q3_K_M) on AMD Strix Halo (Radeon 8060S) with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
229.54 tok/s
Decode
Decode speed
1,241.69 tok/s
Prefill
Prefill speed
2.22 s
TTFT
Time to first token
3.24 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 (current)Decode 229.54 · Prefill 1241.69 ·
- vLLM · IQ3_S Decode 249.57 · Prefill 1015.71 ·
- vLLM · Q3_K_L Decode 238.07 · Prefill 894.22 ·
Core figures
- Decode (avg)
- 229.54 tok/s
- Prefill (avg)
- 1,241.69 tok/s
- TTFT (avg)
- 2.22 s
- VRAM (avg)
- 3.24 GB
- MTP acceptance rate
- —
- TTFB
- 1.84 GB
- Power draw
- 78.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q3_K_M
- Framework
- llama.cpp
- Version
- v0.52
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 33
- 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)
- 3.24 GB
- OS
- Ubuntu 22.04
- Driver
- 560.94
- CUDA
- N/A
- Power draw
- 78.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.52 · Ubuntu 22.04 · CUDA N/A · 4096 ctx
229.54 tok/s
Decode
1,241.69 tok/s
Prefill
2.22 s
TTFT
3.24 GB
VRAM
—
MTP
78.1 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=87 running model_id=51 at Q3_K_M