lfm2:24b-a2b
OLLAMA GGUFlfm2moe · 23.8B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
gemma4:12b-mlx
OLLAMA GGUFJul 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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest