Back to search results
Qwen3.5-0.8B · IQ4_XS
AMD Ryzen AI Max+ 395128GBvLLM v0.32L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ4_XS) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
85.62 tok/s
Decode
Decode speed
384.79 tok/s
Prefill
Prefill speed
2.08 s
TTFT
Time to first token
3.34 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- llama.cpp · IQ2_XS Decode 231.64 · Prefill 936.81 ·
- llama.cpp · Q4_K_M Decode 68.16 · Prefill 362.8 ·
- vLLM · IQ4_XS (current)Decode 85.62 · Prefill 384.79 ·
- llama.cpp · IQ4_XS Decode 273.83 · Prefill 1312.19 ·
- llama.cpp · Q5_K_M Decode 197.9 · Prefill 695.65 ·
- Ollama · Q4_K_M Decode 220.93 · Prefill 741.5 ·
- Ollama · Q8_0 Decode 163.22 · Prefill 720.03 ·
- llama.cpp · IQ1_S Decode 380.54 · Prefill 1677.44 ·
Core figures
- Decode (avg)
- 85.62 tok/s
- Prefill (avg)
- 384.79 tok/s
- TTFT (avg)
- 2.08 s
- VRAM (avg)
- 3.34 GB
- MTP acceptance rate
- —
- TTFB
- 0.68 GB
- Power draw
- 45.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ4_XS
- Framework
- vLLM
- Version
- v0.32
- Context length
- 2048 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- Off
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)
- 3.34 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu-pro 24.20
- CUDA
- 12.6
- Power draw
- 45.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.32 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx
85.62 tok/s
Decode
384.79 tok/s
Prefill
2.08 s
TTFT
3.34 GB
VRAM
—
MTP
45.5 W
Power draw
L2 batch seed 2026-10-19: vLLM on hw_id=24 running model_id=51 at IQ4_XS