Back to search results
Llama-3.1-8B-Instruct · IQ2_M
Apple M5 Max128GBllama.cpp v0.32L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ2_M) on Apple M5 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
101.46 tok/s
Decode
Decode speed
460.44 tok/s
Prefill
Prefill speed
2.43 s
TTFT
Time to first token
10.84 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 · IQ2_M (current)Decode 101.46 · Prefill 460.44 ·
- llama.cpp · Q3_K_L Decode 81.19 · Prefill 358.64 ·
- Ollama · IQ3_XS Decode 82.82 · Prefill 392.75 ·
- Ollama · Q3_K_S Decode 79.81 · Prefill 418 ·
Core figures
- Decode (avg)
- 101.46 tok/s
- Prefill (avg)
- 460.44 tok/s
- TTFT (avg)
- 2.43 s
- VRAM (avg)
- 10.84 GB
- MTP acceptance rate
- —
- TTFB
- 0.81 GB
- Power draw
- 45.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.1-8B-Instruct
- Quantization
- IQ2_M
- Framework
- llama.cpp
- Version
- v0.32
- Context length
- 32768 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)
- 10.84 GB
- OS
- macOS 26.1
- Power draw
- 45.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.32 · macOS 26.1 · 32768 ctx
101.46 tok/s
Decode
460.44 tok/s
Prefill
2.43 s
TTFT
10.84 GB
VRAM
—
MTP
45.5 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=28 running model_id=68 at IQ2_M