Back to leaderboard

mlx-community/gemma-3-4b-it-qat-4bit

LM-STUDIO GGUF
Excellent

Mar 5, 2026 · Apple M4

smollm2:135m

OLLAMA GGUF

llama · 134.52M · F16

Marginal

Mar 2, 2026 · Apple M4

Global Score
80 vs 41
Hardware Fit
100 vs 100
Quality Score
71 vs 15

Hardware

mlx-community/gemm… smollm2:135m
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

mlx-community/gemm… smollm2:135m
Tokens/sec43.2241.0
First chunk428 msN/A
TTFT428 ms39 ms
Load timeN/A0.4 s
Memory usage1.3 GB0.6 GB
Memory %4%2%

HW Fit Score Breakdown

mlx-community/gemma-3-4…

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

smollm2:135m

Speed
40/50
TTFT
30/20
Memory
30/30

Quality

mlx-community/gemma-3-4…

Reasoning
9/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

smollm2:135m

Reasoning
4/20
Coding
1/20
Instruction
6/20
Structured
2/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

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