Back to search results
Qwen3.8-9B · IQ1_S
Intel Arc B58012GBvLLM v0.38L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ1_S) on Intel Arc B580 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
66.31 tok/s
Decode
Decode speed
217.11 tok/s
Prefill
Prefill speed
0.14 s
TTFT
Time to first token
10.04 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ2_M Decode 60.79 · Prefill 239.93 ·
- vLLM · IQ1_S (current)Decode 66.31 · Prefill 217.11 ·
- llama.cpp · IQ2_XS Decode 61.39 · Prefill 302.91 ·
- llama.cpp · IQ3_XS Decode 56.63 · Prefill 277.66 ·
- llama.cpp · Q4_K_M Decode — · Prefill — ·
Core figures
- Decode (avg)
- 66.31 tok/s
- Prefill (avg)
- 217.11 tok/s
- TTFT (avg)
- 0.14 s
- VRAM (avg)
- 10.04 GB
- MTP acceptance rate
- —
- TTFB
- 0.53 GB
- Power draw
- 144 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ1_S
- Framework
- vLLM
- Version
- v0.38
- Context length
- 4096 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
- Intel Arc B580
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 10.04 GB
- OS
- Windows 11 24H2
- Driver
- Intel Arc 32.0.101.6552
- CUDA
- 12.4
- Power draw
- 144 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.38 · Windows 11 24H2 · CUDA 12.4 · 4096 ctx
66.31 tok/s
Decode
217.11 tok/s
Prefill
0.14 s
TTFT
10.04 GB
VRAM
—
MTP
144 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=94 running model_id=52 at IQ1_S