Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16

OLLAMA GGUF

lfm2 · 2.7B · unknown

Good

Aug 26, 2026 · Apple M1 Pro

Global Score
76 vs 61
Hardware Fit
46 vs 97
Quality Score
89 vs 46

Hardware

gemma4:31b hf.co/LiquidAI/LFM…
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M1 Pro
Cores1610
RAM64 GB16 GB
GPUApple M4 MaxApple M1 Pro
OSmacOS 26.3.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:31b hf.co/LiquidAI/LFM…
Tokens/sec22.431.3
First chunk565 ms131 ms
TTFT30.0 s131 ms
Load time6.9 s4.2 s
Memory usage43.9 GB6.6 GB
Memory %69%41%

HW Fit Score Breakdown

gemma4:31b

Speed
30/50
TTFT
0/20
Memory
16/30

hf.co/LiquidAI/LFM2.5-2…

Speed
50/50
TTFT
20/20
Memory
27/30

Quality

gemma4:31b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

hf.co/LiquidAI/LFM2.5-2…

Reasoning
14/20
Coding
13/20
Instruction
3/20
Structured
0/15
Math
14/15
Multilingual
2/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

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