Back to search results
Qwen3-8B · Q3_K_M
Intel Arc B58012GBvLLM v0.35L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q3_K_M) on Intel Arc B580 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
56.47 tok/s
Decode
Decode speed
307.9 tok/s
Prefill
Prefill speed
1.83 s
TTFT
Time to first token
11.4 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · Q3_K_M (current)Decode 56.47 · Prefill 307.9 ·
- Strata · IQ2_M Decode 88.38 · Prefill 340.69 ·
- Strata · Q3_K_M Decode 71.01 · Prefill 283.66 ·
- llama.cpp · Q3_K_M Decode 57.89 · Prefill 216.32 ·
- vLLM · IQ1_S Decode 82.24 · Prefill 450.81 ·
- vLLM · IQ2_XS Decode 78.59 · Prefill 324.5 ·
Core figures
- Decode (avg)
- 56.47 tok/s
- Prefill (avg)
- 307.9 tok/s
- TTFT (avg)
- 1.83 s
- VRAM (avg)
- 11.4 GB
- MTP acceptance rate
- —
- TTFB
- 0.45 GB
- Power draw
- 132.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q3_K_M
- Framework
- vLLM
- Version
- v0.35
- 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
- Intel Arc B580
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 11.4 GB
- OS
- Ubuntu 24.04
- Driver
- Intel Arc 32.0.101.6552
- CUDA
- 12.6
- Power draw
- 132.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.35 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx
56.47 tok/s
Decode
307.9 tok/s
Prefill
1.83 s
TTFT
11.4 GB
VRAM
—
MTP
132.5 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=94 running model_id=53 at Q3_K_M