Raon-1-mini-preview · Q3_K_S
This page aggregates 1 real-world runs of Raon-1-mini-preview (Q3_K_S) on NVIDIA H100 80GB HBM3 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
313.56 tok/s
Decode
Decode speed
1,182.08 tok/s
Prefill
Prefill speed
0.81 s
TTFT
Time to first token
41.41 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
13 days ago
Last verified
Performance
- llama.cpp · Q6_K Decode 343.53 · Prefill 1745.18 ·
- Ollama · Q3_K_S (current)Decode 313.56 · Prefill 1182.08 ·
Core figures
- Decode (avg)
- 313.56 tok/s
- Prefill (avg)
- 1,182.08 tok/s
- TTFT (avg)
- 0.81 s
- VRAM (avg)
- 41.41 GB
- MTP acceptance rate
- —
- TTFB
- 2.51 GB
- Power draw
- 563 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Raon-1-mini-preview
- Quantization
- Q3_K_S
- Framework
- Ollama
- Version
- v0.52
- 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
- NVIDIA H100 80GB HBM3
- Nominal VRAM
- 80 GB
- Measured VRAM (avg)
- 41.41 GB
- OS
- Ubuntu 22.04
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 563 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
v0.52 · Ubuntu 22.04 · CUDA 12.8 · 32768 ctx
313.56 tok/s
Decode
1,182.08 tok/s
Prefill
0.81 s
TTFT
41.41 GB
VRAM
—
MTP
563 W
Power draw
L2 batch seed 2026-10-22: Ollama on hw_id=55 running model_id=93 at Q3_K_S