Back to leaderboard

mlx-community/quantized-gemma-2b-it

LM-STUDIO GGUF
Marginal

Mar 5, 2026 · Apple M4

nemotron-3-nano:4b

OLLAMA GGUF

nemotron_h · 4.0B · Q4_K_M

Excellent

Aug 25, 2026 · Apple M1 Pro

Global Score
45 vs 85
Hardware Fit
100 vs 100
Quality Score
21 vs 78

Hardware

mlx-community/quan… nemotron-3-nano:4b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

mlx-community/quan… nemotron-3-nano:4b
Tokens/sec44.431.7
First chunk336 ms265 ms
TTFT336 ms265 ms
Load timeN/A2.2 s
Memory usage0.1 GB4.1 GB
Memory %0%25%

HW Fit Score Breakdown

mlx-community/quantized…

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

nemotron-3-nano:4b

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

Quality

mlx-community/quantized…

Reasoning
4/20
Coding
1/20
Instruction
9/20
Structured
4/15
Math
2/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Poor

nemotron-3-nano:4b

Reasoning
16/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View mlx-community/quan… details | View nemotron-3-nano:4b 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