Back to search results
Qwen3-1.7B · Q3_K_L
AMD Strix Halo (Radeon 8060S)vLLM v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_L) on AMD Strix Halo (Radeon 8060S) with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
174.98 tok/s
Decode
Decode speed
636.17 tok/s
Prefill
Prefill speed
0.72 s
TTFT
Time to first token
4.67 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 · Q2_K Decode 188.51 · Prefill 863.98 ·
- llama.cpp · Q3_K_L Decode 168.83 · Prefill 829.48 ·
- vLLM · Q3_K_L (current)Decode 174.98 · Prefill 636.17 ·
Core figures
- Decode (avg)
- 174.98 tok/s
- Prefill (avg)
- 636.17 tok/s
- TTFT (avg)
- 0.72 s
- VRAM (avg)
- 4.67 GB
- MTP acceptance rate
- —
- TTFB
- 1.4 GB
- Power draw
- 83.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q3_K_L
- Framework
- vLLM
- Version
- v0.40
- Context length
- 4096 tokens
- Batch size
- 16
- 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)
- 4.67 GB
- OS
- Windows 11 23H2
- Driver
- 565.57
- CUDA
- N/A
- Power draw
- 83.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · Windows 11 23H2 · CUDA N/A · 4096 ctx
174.98 tok/s
Decode
636.17 tok/s
Prefill
0.72 s
TTFT
4.67 GB
VRAM
—
MTP
83.2 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=87 running model_id=55 at Q3_K_L