Back to search results
Qwen3.5-0.8B · Q3_K_L
AMD Strix Halo (Radeon 8060S)llama.cpp v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q3_K_L) on AMD Strix Halo (Radeon 8060S) with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
205.24 tok/s
Decode
Decode speed
943.68 tok/s
Prefill
Prefill speed
1.06 s
TTFT
Time to first token
3.31 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 (current)Decode 205.24 · Prefill 943.68 ·
- llama.cpp · Q3_K_M 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)
- 205.24 tok/s
- Prefill (avg)
- 943.68 tok/s
- TTFT (avg)
- 1.06 s
- VRAM (avg)
- 3.31 GB
- MTP acceptance rate
- —
- TTFB
- 1.64 GB
- Power draw
- 95.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q3_K_L
- Framework
- llama.cpp
- Version
- v0.50
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 99
- 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)
- 3.31 GB
- OS
- Ubuntu 24.04
- Driver
- 555.85
- CUDA
- N/A
- Power draw
- 95.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · Ubuntu 24.04 · CUDA N/A · 16384 ctx
205.24 tok/s
Decode
943.68 tok/s
Prefill
1.06 s
TTFT
3.31 GB
VRAM
—
MTP
95.8 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=87 running model_id=51 at Q3_K_L