ministral-3-14b-instruct-2512

mistral3 · 14B · Q5_K_M

ECO MODE

ASUS (AMD Ryzen 7 7800X3D 8-Core Processor)

31 GB · cachyos rolling

Tested on July 4, 2026

Top 20% Compare

Global Score

83 /100

Excellent

Hardware Fit

90/100

Quality

80/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: ASUS
CPU: AMD Ryzen 7 7800X3D 8-Core Processor
Cores: 16 threads (8 cores)
Frequency: 2.55 GHz
RAM: 31 GB
GPU: NVIDIA GeForce RTX 4090, Raphael
OS: cachyos rolling
Arch: x64
Power Mode: low-power

Performance

Tokens/sec Tokens generated per second — higher is better: 83.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 16 ms
Time to first token How fast the model starts responding — lower is better: 117 ms
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 18.2 GB (60%)
Total tokens Total number of tokens generated across all benchmark prompts: 1146

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

20/30

Quality

Reasoning

17/20

Coding

17/20

Instruction following

15/20

Structured output

14/15

Math

7/15

Multilingual

10/10

Category levels

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: LM Studio
Model format: GGUF
Hardware profile: BALANCED
Result hash: b59fb7ea35e786ab2fc9f3cb2a1f9215d07873346bd6f3e4217230ec59a1b242

Interpretation

Hardware fit: 90/100. Overall suitability: EXCELLENT (Global 83/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.
System was in low-power mode during this benchmark.

Bench Environment

Thermal: nominal CPU load: avg 10% (peak 21%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest