devstral-small-2-24b-instruct-2512

mistral3 · 24B · IQ4_XS

System manufacturer (AMD Ryzen 7 5800X 8-Core Processor)

31 GB · Ubuntu 26.04.1 LTS

Tested on September 20, 2026

Top 38% Compare

Global Score

81 /100

Excellent

Hardware Fit

80/100

Quality

81/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: System manufacturer
CPU: AMD Ryzen 7 5800X 8-Core Processor
Cores: 16 threads (8 cores)
Frequency: 3.8 GHz
RAM: 31 GB
GPU: Navi 44 [Radeon RX 9060 XT]
OS: Ubuntu 26.04.1 LTS
Arch: x64
Power Mode: performance

Performance

Tokens/sec Tokens generated per second — higher is better: 21.5
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.0
First chunk latency Delay before the first streamed chunk arrives from runtime: 12 ms
Time to first token How fast the model starts responding — lower is better: 212 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: 15.9 GB (51%)
Total tokens Total number of tokens generated across all benchmark prompts: 1008

Score breakdown

Speed

35/50

Time to first token

20/20

Memory

25/30

Quality

Reasoning

16/20

Coding

17/20

Instruction following

17/20

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: 681d7548d9a677049183806dd4b80658f2c156d51854b8e110889e38878fa353

Interpretation

Hardware fit: 80/100. Overall suitability: EXCELLENT (Global 81/100). 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.

Bench Environment

Thermal: nominal CPU load: avg 7% (peak 8%)

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