Back to leaderboard

lfm2.5-thinking:1.2b

OLLAMA GGUF

lfm2 · 1.2B · Q4_K_M

Not Rec.

May 25, 2026 · Apple M4 Pro

gemma-4-31b-it-qat

LM-STUDIO GGUF

gemma4 · 31B · Q4_K_XL

Excellent

Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
60 vs 91
Hardware Fit
80 vs 89
Quality Score
52 vs 92

Hardware

lfm2.5-thinking:1.2b gemma-4-31b-it-qat
MachineMacBook ProASUS
CPUApple M4 ProAMD Ryzen 7 7800X3D 8-Core Processor
Cores1416
RAM48 GB31 GB
GPUApple M4 ProNVIDIA GeForce RTX 4090, Raphael
OSmacOS 26.4.1cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

lfm2.5-thinking:1.2b gemma-4-31b-it-qat
Tokens/sec227.040.2
First chunk60 ms3 ms
TTFT30.0 s302 ms
Load time0.7 sN/A
Memory usage2.6 GB18.8 GB
Memory %6%62%

HW Fit Score Breakdown

lfm2.5-thinking:1.2b

Speed
50/50
TTFT
0/20
Memory
30/30

gemma-4-31b-it-qat

Speed
50/50
TTFT
20/20
Memory
19/30

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

gemma-4-31b-it-qat

Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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