mistralai/magistral-small-2509

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

nemotron-3-nano:latest

OLLAMA GGUF

nemotron_h_moe · 31.6B · Q4_K_M

Excellent

Mar 13, 2026 · AMD RYZEN AI MAX+ 395

Global Score

74 vs 87

Hardware Fit

66 vs 100

Quality Score

78 vs 82

Hardware

mistralai/magistra… nemotron-3-nano:la…

MachineMacBook AirAZW GTR Pro

CPUApple M4AMD RYZEN AI MAX+ 395

Cores1032

RAM32 GB125 GB

GPUApple M4Radeon 8060S

OSmacOS 26.3Ubuntu 24.04.4 LTS

Archarm64x64

Power Modebalancedperformance

Performance

mistralai/magistra… nemotron-3-nano:la…

Tokens/sec7.959.9

First chunk1356 ms199 ms

TTFT1.4 s199 ms

Load timeN/A0.1 s

Memory usage13.2 GB26.0 GB

Memory %41%21%

HW Fit Score Breakdown

mistralai/magistral-sma…

Speed

16/50

TTFT

20/20

Memory

30/30

nemotron-3-nano:latest

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

mistralai/magistral-sma…

Reasoning

14/20

Coding

18/20

Instruction

14/20

Structured

15/15

Math

7/15

Multilingual

10/10

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

nemotron-3-nano:latest

Reasoning

16/20

Coding

18/20

Instruction

16/20

Structured

15/15

Math

7/15

Multilingual

10/10

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

View mistralai/magistra… details | View nemotron-3-nano:la… details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest