Back to search results
Qwen3.8-9B · IQ2_XS
Intel Arc B58012GBllama.cpp v0.36L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ2_XS) on Intel Arc B580 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
61.39 tok/s
Decode
Decode speed
302.91 tok/s
Prefill
Prefill speed
1.19 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
Today
Last verified
Performance
- llama.cpp · IQ2_XS (current)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)
- 61.39 tok/s
- Prefill (avg)
- 302.91 tok/s
- TTFT (avg)
- 1.19 s
- VRAM (avg)
- 11.17 GB
- MTP acceptance rate
- —
- TTFB
- 0.49 GB
- Power draw
- 279 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ2_XS
- Framework
- llama.cpp
- Version
- v0.36
- Context length
- 4096 tokens
- Batch size
- 256
- GPU layers
- 99
- 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)
- 11.17 GB
- OS
- Ubuntu 24.04
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 279 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.36 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx
61.39 tok/s
Decode
302.91 tok/s
Prefill
1.19 s
TTFT
11.17 GB
VRAM
—
MTP
279 W
Power draw
L2 batch seed 2026-10-10: llama.cpp on hw_id=94 running model_id=52 at IQ2_XS