Back to search results
Ministral-3-8B-Instruct-2512 · Q4_K_S
NVIDIA RTX 508016GBllama.cpp v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Ministral-3-8B-Instruct-2512 (Q4_K_S) on NVIDIA RTX 5080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
176.14 tok/s
Decode
Decode speed
941.33 tok/s
Prefill
Prefill speed
0.6 s
TTFT
Time to first token
15.2 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
12 days ago
Last verified
Performance
- llama.cpp · Q4_K_S (current)Decode 176.14 · Prefill 941.33 ·
Core figures
- Decode (avg)
- 176.14 tok/s
- Prefill (avg)
- 941.33 tok/s
- TTFT (avg)
- 0.6 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 1.41 GB
- Power draw
- 269.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Ministral-3-8B-Instruct-2512
- Quantization
- Q4_K_S
- Framework
- llama.cpp
- Version
- v0.31
- Context length
- 32768 tokens
- Batch size
- 512
- 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 RTX 5080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 15.2 GB
- OS
- Windows 11 24H2
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 269.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · Windows 11 24H2 · CUDA 12.8 · 32768 ctx
176.14 tok/s
Decode
941.33 tok/s
Prefill
0.6 s
TTFT
15.2 GB
VRAM
—
MTP
269.7 W
Power draw
L2 batch seed 2026-10-24: llama.cpp on hw_id=14 running model_id=74 at Q4_K_S