Back to search results
Ministral-3-8B-Instruct-2512 · IQ4_XS
NVIDIA RTX 507012GBStrata 0.5.2L0 Self-reported
This page aggregates 1 real-world runs of Ministral-3-8B-Instruct-2512 (IQ4_XS) on NVIDIA RTX 5070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
156.3 tok/s
Decode
Decode speed
1,172.3 tok/s
Prefill
Prefill speed
0.09 s
TTFT
Time to first token
4.8 GB
VRAM
VRAM usage
L0 Self-reported
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- Strata · IQ4_XS (current)Decode 156.3 · Prefill 1172.3 ·
Core figures
- Decode (avg)
- 156.3 tok/s
- Prefill (avg)
- 1,172.3 tok/s
- TTFT (avg)
- 0.09 s
- VRAM (avg)
- 4.8 GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- — W
Configuration
Member-level fields are taken from the most recent run
- Model
- Ministral-3-8B-Instruct-2512
- Quantization
- IQ4_XS
- Framework
- Strata
- Version
- 0.5.2
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5070
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 4.8 GB
- OS
- Linux
- Driver
- 570.65
- CUDA
- 12.6
Sources & evidence
1 measured records in total, each traceable to its original source
0.5.2 · Linux · CUDA 12.6 · 4096 ctx
156.3 tok/s
Decode
1,172.3 tok/s
Prefill
0.09 s
TTFT
4.8 GB
VRAM
—
MTP
— W
Power draw
L0 理论估算