lfm2:24b-a2b
OLLAMA GGUFlfm2moe · 23.8B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
gemma3:12b
OLLAMA GGUFgemma3 · 12.2B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
78 vs 80
Hardware Fit
67 vs 83
Quality Score
82 vs 78
Hardware
lfm2:24b-a2b gemma3:12b
MachineDell Inc. Inspiron 15 3530MacBook Air
CPUIntel Gen Intel® Core™ i7-1355UApple M4
Cores1210
RAM31 GB32 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M4
OScachyos rollingmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
lfm2:24b-a2b gemma3:12b
Tokens/sec11.512.7
First chunk1727 msN/A
TTFT1.7 s560 ms
Load time6.8 s2.8 s
Memory usage13.9 GB11.0 GB
Memory %45%34%
HW Fit Score Breakdown
lfm2:24b-a2b
Speed
22/50
TTFT
19/20
Memory
26/30
gemma3:12b
Speed
23/50
TTFT
30/20
Memory
30/30
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
gemma3:12b
Reasoning
14/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
7/15
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