Back to leaderboard

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

LM-STUDIO GGUF
Marginal

Mar 5, 2026 · Apple M4

falcon3-1b-instruct

LM-STUDIO MLX

llama · 1B · 3bit

Marginal

Mar 4, 2026 · Apple M4

Global Score
45 vs 54
Hardware Fit
100 vs 100
Quality Score
21 vs 34

Hardware

mlx-community/quan… falcon3-1b-instruct
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

mlx-community/quan… falcon3-1b-instruct
Tokens/sec44.4121.8
First chunk336 ms176 ms
TTFT336 ms176 ms
Load timeN/AN/A
Memory usage0.1 GB0.7 GB
Memory %0%2%

HW Fit Score Breakdown

mlx-community/quantized…

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

falcon3-1b-instruct

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

falcon3-1b-instruct

Reasoning
7/20
Coding
1/20
Instruction
12/20
Structured
7/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor Multilingual: Weak
View mlx-community/quan… details | View falcon3-1b-instruct 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