Back to leaderboard

liquid/lfm2-24b-a2b

LM-STUDIO MLX

lfm2_moe · 24B · 4bit

Good

Apr 1, 2026 · Apple M4

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

Aug 22, 2026 · Apple M1 Pro

Global Score
74 vs 63
Hardware Fit
84 vs 62
Quality Score
69 vs 63

Hardware

liquid/lfm2-24b-a2b gemma4:12b
MachineMac miniMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM24 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

liquid/lfm2-24b-a2b gemma4:12b
Tokens/sec51.815.3
First chunk10 ms1142 ms
TTFT503 ms30.0 s
Load timeN/A5.4 s
Memory usage17.5 GB7.6 GB
Memory %73%47%

HW Fit Score Breakdown

liquid/lfm2-24b-a2b

Speed
50/50
TTFT
20/20
Memory
14/30

gemma4:12b

Speed
36/50
TTFT
0/20
Memory
26/30

Quality

liquid/lfm2-24b-a2b

Reasoning
11/20
Coding
12/20
Instruction
16/20
Structured
13/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma4:12b

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