Back to search results
Qwen3.8-9B · IQ2_XS
AMD Ryzen AI Max+ 395128GBvLLM v0.38L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ2_XS) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
145.04 tok/s
Decode
Decode speed
523.91 tok/s
Prefill
Prefill speed
2.01 s
TTFT
Time to first token
11.17 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 · IQ2_M Decode 125.51 · Prefill 634.19 ·
- llama.cpp · IQ3_S Decode 115.85 · Prefill 489.76 ·
- vLLM · Q5_K_M Decode 82.89 · Prefill 274.27 ·
- vLLM · IQ2_XS (current)Decode 145.04 · Prefill 523.91 ·
- vLLM · Q3_K_L Decode 107.95 · Prefill 386.71 ·
- Strata · IQ3_XS Decode 164.91 · Prefill 583.87 ·
- Strata · Q5_K_S Decode 114.19 · Prefill 509.48 ·
Core figures
- Decode (avg)
- 145.04 tok/s
- Prefill (avg)
- 523.91 tok/s
- TTFT (avg)
- 2.01 s
- VRAM (avg)
- 11.17 GB
- MTP acceptance rate
- —
- TTFB
- 1.16 GB
- Power draw
- 119.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ2_XS
- Framework
- vLLM
- Version
- v0.38
- Context length
- 32768 tokens
- Batch size
- 32
- 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)
- 11.17 GB
- OS
- Windows 11 23H2
- Driver
- AMD Adrenalin 25.10.1
- CUDA
- N/A
- Power draw
- 119.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.38 · Windows 11 23H2 · CUDA N/A · 32768 ctx
145.04 tok/s
Decode
523.91 tok/s
Prefill
2.01 s
TTFT
11.17 GB
VRAM
—
MTP
119.8 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=24 running model_id=52 at IQ2_XS