Back to search results
Llama-3.1-8B-Instruct · IQ3_S
Intel Arc B58012GBllama.cpp v0.41L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ3_S) on Intel Arc B580 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
58.55 tok/s
Decode
Decode speed
274.06 tok/s
Prefill
Prefill speed
1.35 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
17 days ago
Last verified
Performance
- llama.cpp · IQ3_S (current)Decode 58.55 · Prefill 274.06 ·
- llama.cpp · Q3_K_S Decode 65.46 · Prefill 319.04 ·
- Ollama · IQ2_XS Decode 70.97 · Prefill 264.22 ·
- Ollama · IQ2_M Decode 67.87 · Prefill 259.33 ·
Core figures
- Decode (avg)
- 58.55 tok/s
- Prefill (avg)
- 274.06 tok/s
- TTFT (avg)
- 1.35 s
- VRAM (avg)
- 11.4 GB
- MTP acceptance rate
- —
- TTFB
- 0.47 GB
- Power draw
- 160.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.1-8B-Instruct
- Quantization
- IQ3_S
- Framework
- llama.cpp
- Version
- v0.41
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- Off
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
- Windows 11 24H2
- Driver
- Intel Arc 32.0.101.6552
- CUDA
- 12.6
- Power draw
- 160.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.41 · Windows 11 24H2 · CUDA 12.6 · 4096 ctx
58.55 tok/s
Decode
274.06 tok/s
Prefill
1.35 s
TTFT
11.4 GB
VRAM
—
MTP
160.7 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=94 running model_id=68 at IQ3_S