Back to leaderboard

lfm2:24b-a2b

OLLAMA GGUF

lfm2moe · 23.8B · Q4_K_M

Good

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

gemma-3-27b-it-qat

LM-STUDIO MLX

gemma3 · 27B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

Global Score
78 vs 76
Hardware Fit
67 vs 51
Quality Score
82 vs 87

Hardware

lfm2:24b-a2b gemma-3-27b-it-qat
MachineDell Inc. Inspiron 15 3530Mac mini
CPUIntel Gen Intel® Core™ i7-1355UApple M4 Pro
Cores1214
RAM31 GB64 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M4 Pro
OScachyos rollingmacOS 15.7.4
Archx64arm64
Power Modelow-powerbalanced

Performance

lfm2:24b-a2b gemma-3-27b-it-qat
Tokens/sec11.58.9
First chunk1727 ms3976 ms
TTFT1.7 s4.0 s
Load time6.8 sN/A
Memory usage13.9 GB15.7 GB
Memory %45%25%

HW Fit Score Breakdown

lfm2:24b-a2b

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

gemma-3-27b-it-qat

Speed
12/50
TTFT
9/20
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

gemma-3-27b-it-qat

Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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