mlx-community/gemma-3-1b-it-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
Global Score
72 vs 60
Hardware Fit
99 vs 80
Quality Score
61 vs 52
Hardware
mlx-community/gemm… lfm2.5-thinking:1.2b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M4 Pro
Cores1014
RAM32 GB48 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/gemm… lfm2.5-thinking:1.2b
Tokens/sec86.3227.0
First chunk253 ms60 ms
TTFT253 ms30.0 s
Load timeN/A0.7 s
Memory usage1.1 GB2.6 GB
Memory %4%6%
HW Fit Score Breakdown
mlx-community/gemma-3-1…
Speed
50/50
TTFT
20/20
Memory
29/30
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
mlx-community/gemma-3-1…
Reasoning
7/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
2/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
lfm2.5-thinking:1.2b
Reasoning
8/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
12/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest