lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
60 vs 90
Hardware Fit
80 vs 78
Quality Score
52 vs 95
Hardware
lfm2.5-thinking:1.2b gemma4:e4b-mlx
MachineMacBook ProMacBook Pro
CPUApple M4 ProApple M2 Pro
Cores1410
RAM48 GB16 GB
GPUApple M4 ProApple M2 Pro
OSmacOS 26.4.1macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
lfm2.5-thinking:1.2b gemma4:e4b-mlx
Tokens/sec227.046.1
First chunk60 ms284 ms
TTFT30.0 s3.9 s
Load time0.7 s0.1 s
Memory usage2.6 GB10.8 GB
Memory %6%68%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
gemma4:e4b-mlx
Speed
50/50
TTFT
12/20
Memory
16/30
Quality
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
gemma4:e4b-mlx
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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