Raon-1-mini-preview · Q8_0
This page aggregates 1 real-world runs of Raon-1-mini-preview (Q8_0) on Apple M5 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
76.11 tok/s
Decode
Decode speed
389.07 tok/s
Prefill
Prefill speed
1.36 s
TTFT
Time to first token
71.65 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
13 days ago
Last verified
Performance
- llama.cpp · Q8_0 (current)Decode 76.11 · Prefill 389.07 ·
- Ollama · Q4_K_S Decode 118.22 · Prefill 450.95 ·
Core figures
- Decode (avg)
- 76.11 tok/s
- Prefill (avg)
- 389.07 tok/s
- TTFT (avg)
- 1.36 s
- VRAM (avg)
- 71.65 GB
- MTP acceptance rate
- —
- TTFB
- 0.61 GB
- Power draw
- 114.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Raon-1-mini-preview
- Quantization
- Q8_0
- Framework
- llama.cpp
- Version
- v0.47
- Context length
- 4096 tokens
- Batch size
- 512
- 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
- Apple M5 Ultra
- Nominal VRAM
- 512 GB
- Measured VRAM (avg)
- 71.65 GB
- OS
- macOS 26.1
- Power draw
- 114.3 W
Get started
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · macOS 26.1 · 4096 ctx
76.11 tok/s
Decode
389.07 tok/s
Prefill
1.36 s
TTFT
71.65 GB
VRAM
—
MTP
114.3 W
Power draw
L2 batch seed 2026-10-22: llama.cpp on hw_id=29 running model_id=93 at Q8_0