Back to search results
Qwen3-1.7B · Q8_0
AMD Ryzen AI Max+ 395128GBvLLM v0.44L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q8_0) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
132.62 tok/s
Decode
Decode speed
633.28 tok/s
Prefill
Prefill speed
0.38 s
TTFT
Time to first token
6.21 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · Q4_K_M Decode 187.84 · Prefill 854.19 ·
- vLLM · IQ1_S Decode 304.08 · Prefill 1413.06 ·
- llama.cpp · Q5_K_M Decode 145.14 · Prefill 763.75 ·
- vLLM · IQ3_S Decode 246.99 · Prefill 860.32 ·
- vLLM · Q8_0 (current)Decode 132.62 · Prefill 633.28 ·
Core figures
- Decode (avg)
- 132.62 tok/s
- Prefill (avg)
- 633.28 tok/s
- TTFT (avg)
- 0.38 s
- VRAM (avg)
- 6.21 GB
- MTP acceptance rate
- —
- TTFB
- 1.06 GB
- Power draw
- 66.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q8_0
- Framework
- vLLM
- Version
- v0.44
- Context length
- 8192 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 Ryzen AI Max+ 395
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 6.21 GB
- OS
- Windows 11 23H2
- Driver
- AMD Adrenalin 25.10.1
- CUDA
- N/A
- Power draw
- 66.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · Windows 11 23H2 · CUDA N/A · 8192 ctx
132.62 tok/s
Decode
633.28 tok/s
Prefill
0.38 s
TTFT
6.21 GB
VRAM
—
MTP
66.5 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=24 running model_id=55 at Q8_0