Back to search results
Llama-3.2-3B-Instruct · IQ3_XS
Apple M5 Max128GBOllama v0.46L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (IQ3_XS) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
209.81 tok/s
Decode
Decode speed
739.8 tok/s
Prefill
Prefill speed
1.63 s
TTFT
Time to first token
6.01 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 · Q4_K_S Decode 188.34 · Prefill 664.86 ·
- Ollama · IQ3_XS (current)Decode 209.81 · Prefill 739.8 ·
Core figures
- Decode (avg)
- 209.81 tok/s
- Prefill (avg)
- 739.8 tok/s
- TTFT (avg)
- 1.63 s
- VRAM (avg)
- 6.01 GB
- MTP acceptance rate
- —
- TTFB
- 1.68 GB
- Power draw
- 53.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.2-3B-Instruct
- Quantization
- IQ3_XS
- Framework
- Ollama
- Version
- v0.46
- Context length
- 8192 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
- Apple M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 6.01 GB
- OS
- macOS 26.1
- Power draw
- 53.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.46 · macOS 26.1 · 8192 ctx
209.81 tok/s
Decode
739.8 tok/s
Prefill
1.63 s
TTFT
6.01 GB
VRAM
—
MTP
53.2 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=28 running model_id=70 at IQ3_XS