lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
gemma3:4b
OLLAMA GGUFgemma3 · 4.3B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
60 vs 76
Hardware Fit
80 vs 92
Quality Score
52 vs 69
Hardware
lfm2.5-thinking:1.2b gemma3:4b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4 ProCortex-A78AE
Cores146
RAM48 GB7 GB
GPUApple M4 ProIntegrated / Unknown
OSmacOS 26.4.1Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
lfm2.5-thinking:1.2b gemma3:4b
Tokens/sec227.015.0
First chunk60 ms2380 ms
TTFT30.0 s2.4 s
Load time0.7 s13.6 s
Memory usage2.6 GB2.6 GB
Memory %6%35%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
gemma3:4b
Speed
45/50
TTFT
18/20
Memory
29/30
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
gemma3:4b
Reasoning
11/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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