Back to leaderboard

lfm2:24b-a2b

OLLAMA GGUF

lfm2moe · 23.8B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

gemma4:12b-mlx

OLLAMA GGUF
Excellent

Jul 4, 2026 · Apple M2 Pro

Global Score
78 vs 81
Hardware Fit
67 vs 82
Quality Score
82 vs 81

Hardware

lfm2:24b-a2b gemma4:12b-mlx
MachineDell Inc. Inspiron 15 3530MacBook Pro
CPUIntel Gen Intel® Core™ i7-1355UApple M2 Pro
Cores1210
RAM31 GB16 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M2 Pro
OScachyos rollingmacOS 26.5
Archx64arm64
Power Modelow-powerbalanced

Performance

lfm2:24b-a2b gemma4:12b-mlx
Tokens/sec11.525.3
First chunk1727 ms761 ms
TTFT1.7 s7.7 s
Load time6.8 s3.6 s
Memory usage13.9 GB7.1 GB
Memory %45%44%

HW Fit Score Breakdown

lfm2:24b-a2b

Speed
22/50
TTFT
19/20
Memory
26/30

gemma4:12b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

Quality

lfm2:24b-a2b

Reasoning
13/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma4:12b-mlx

Reasoning
16/20
Coding
15/20
Instruction
12/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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