Raon-1-mini-preview · Q6_K
This page aggregates 1 real-world runs of Raon-1-mini-preview (Q6_K) on NVIDIA H100 80GB HBM3 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
343.53 tok/s
Decode
Decode speed
1,745.18 tok/s
Prefill
Prefill speed
0.71 s
TTFT
Time to first token
62.58 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
14 days ago
Last verified
Performance
- llama.cpp · Q6_K (current)Decode 343.53 · Prefill 1745.18 ·
- Ollama · Q3_K_S Decode 313.56 · Prefill 1182.08 ·
Core figures
- Decode (avg)
- 343.53 tok/s
- Prefill (avg)
- 1,745.18 tok/s
- TTFT (avg)
- 0.71 s
- VRAM (avg)
- 62.58 GB
- MTP acceptance rate
- —
- TTFB
- 2.75 GB
- Power draw
- 618.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Raon-1-mini-preview
- Quantization
- Q6_K
- Framework
- llama.cpp
- Version
- v0.24
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA H100 80GB HBM3
- Nominal VRAM
- 80 GB
- Measured VRAM (avg)
- 62.58 GB
- OS
- Ubuntu 22.04
- Driver
- 560.94
- CUDA
- 13.0
- Power draw
- 618.1 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
v0.24 · Ubuntu 22.04 · CUDA 13.0 · 2048 ctx
343.53 tok/s
Decode
1,745.18 tok/s
Prefill
0.71 s
TTFT
62.58 GB
VRAM
—
MTP
618.1 W
Power draw
L2 batch seed 2026-10-22: llama.cpp on hw_id=55 running model_id=93 at Q6_K