Back to search results
Llama-3.2-3B-Instruct · FP16
Intel Arc B58012GBOllama v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (FP16) on Intel Arc B580 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
62.55 tok/s
Decode
Decode speed
296.07 tok/s
Prefill
Prefill speed
0.3 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
16 days ago
Last verified
Performance
- llama.cpp · Q2_K Decode 169.62 · Prefill 813.51 ·
- llama.cpp · Q5_K_S Decode 120.67 · Prefill 490.78 ·
- Ollama · FP16 (current)Decode 62.55 · Prefill 296.07 ·
- vLLM · IQ3_XS Decode 157.7 · Prefill 718.89 ·
- vLLM · Q4_K_M Decode 135.38 · Prefill 477.15 ·
- Strata · FP16 Decode 92 · Prefill 368.95 ·
- Strata · Q4_K_M Decode 163.66 · Prefill 710.01 ·
Core figures
- Decode (avg)
- 62.55 tok/s
- Prefill (avg)
- 296.07 tok/s
- TTFT (avg)
- 0.3 s
- VRAM (avg)
- 11.4 GB
- MTP acceptance rate
- —
- TTFB
- 0.5 GB
- Power draw
- 151.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.2-3B-Instruct
- Quantization
- FP16
- Framework
- Ollama
- Version
- v0.26
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 20
- 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
- Windows 11 24H2
- Driver
- Intel Arc 32.0.101.6552
- CUDA
- 12.6
- Power draw
- 151.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · Windows 11 24H2 · CUDA 12.6 · 2048 ctx
62.55 tok/s
Decode
296.07 tok/s
Prefill
0.3 s
TTFT
11.4 GB
VRAM
—
MTP
151.6 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=94 running model_id=70 at FP16