mammoth-1 · Q4_K_M
This page aggregates 1 real-world runs of mammoth-1 (Q4_K_M) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
11.03 tok/s
Decode
Decode speed
58.41 tok/s
Prefill
Prefill speed
1.92 s
TTFT
Time to first token
48.59 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
13 days ago
Last verified
Performance
- llama.cpp · IQ1_S Decode 15.77 · Prefill 62.48 ·
- llama.cpp · Q4_K_M (current)Decode 11.03 · Prefill 58.41 ·
- llama.cpp · Q4_K_S Decode 11.75 · Prefill 39.19 ·
- Ollama · IQ3_S Decode 12.19 · Prefill 51.57 ·
- Ollama · IQ4_XS Decode 9.95 · Prefill 46.04 ·
- Ollama · Q4_K_M Decode 9.21 · Prefill 45.35 ·
Core figures
- Decode (avg)
- 11.03 tok/s
- Prefill (avg)
- 58.41 tok/s
- TTFT (avg)
- 1.92 s
- VRAM (avg)
- 48.59 GB
- MTP acceptance rate
- —
- TTFB
- 0.09 GB
- Power draw
- 75.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- mammoth-1
- Quantization
- Q4_K_M
- Framework
- llama.cpp
- Version
- v0.38
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX Spark
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 48.59 GB
- OS
- Ubuntu 24.04
- Driver
- 615.78
- CUDA
- 13.0
- Power draw
- 75.3 W
- Reference price
- $2,399 · updated 2026-10-19
Prices are not live; check the store page
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
v0.38 · Ubuntu 24.04 · CUDA 13.0 · 8192 ctx
11.03 tok/s
Decode
58.41 tok/s
Prefill
1.92 s
TTFT
48.59 GB
VRAM
—
MTP
75.3 W
Power draw
L2 batch seed 2026-10-22: llama.cpp on hw_id=110 running model_id=94 at Q4_K_M