mammoth-1 · Q4_K_S
This page aggregates 1 real-world runs of mammoth-1 (Q4_K_S) on NVIDIA H100 80GB HBM3 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
342.54 tok/s
Decode
Decode speed
1,113.53 tok/s
Prefill
Prefill speed
2.31 s
TTFT
Time to first token
46.33 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
13 days ago
Last verified
Performance
- llama.cpp · Q4_K_S (current)Decode 342.54 · Prefill 1113.53 ·
- Strata · Q3_K_S Decode 345.96 · Prefill 1251.15 ·
Core figures
- Decode (avg)
- 342.54 tok/s
- Prefill (avg)
- 1,113.53 tok/s
- TTFT (avg)
- 2.31 s
- VRAM (avg)
- 46.33 GB
- MTP acceptance rate
- —
- TTFB
- 2.74 GB
- Power draw
- 634 W
Configuration
Member-level fields are taken from the most recent run
- Model
- mammoth-1
- Quantization
- Q4_K_S
- Framework
- llama.cpp
- Version
- v0.28
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- Off
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)
- 46.33 GB
- OS
- Ubuntu 22.04
- Driver
- 565.57
- CUDA
- 13.0
- Power draw
- 634 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
v0.28 · Ubuntu 22.04 · CUDA 13.0 · 16384 ctx
342.54 tok/s
Decode
1,113.53 tok/s
Prefill
2.31 s
TTFT
46.33 GB
VRAM
—
MTP
634 W
Power draw
L2 batch seed 2026-10-22: llama.cpp on hw_id=55 running model_id=94 at Q4_K_S