Back to leaderboard

mlx-community/Llama-3.2-1B-Instruct-4bit

LM-STUDIO GGUF
Marginal

Mar 5, 2026 · Apple M4

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

LM-STUDIO GGUF

mistral3 · 24B · IQ4_XS

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
57 vs 81
Hardware Fit
100 vs 80
Quality Score
39 vs 81

Hardware

mlx-community/Llam… devstral-small-2-2…
MachineMacBook AirSystem manufacturer
CPUApple M4AMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM32 GB31 GB
GPUApple M4Navi 44 [Radeon RX 9060 XT]
OSmacOS 26.3Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance

Performance

mlx-community/Llam… devstral-small-2-2…
Tokens/sec126.421.5
First chunk139 ms12 ms
TTFT139 ms212 ms
Load timeN/AN/A
Memory usage0.3 GB15.9 GB
Memory %1%51%

HW Fit Score Breakdown

mlx-community/Llama-3.2…

Speed
50/50
TTFT
20/20
Memory
30/30

devstral-small-2-24b-in…

Speed
35/50
TTFT
20/20
Memory
25/30

Quality

mlx-community/Llama-3.2…

Reasoning
5/20
Coding
3/20
Instruction
15/20
Structured
10/15
Math
1/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Strong Structured Output: Adequate Math: Poor Multilingual: Adequate

devstral-small-2-24b-in…

Reasoning
16/20
Coding
17/20
Instruction
17/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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