Back to leaderboard

lfm2-24b-a2b

LM-STUDIO GGUF
Not Rec.

Mar 6, 2026 · Apple M4 Pro

phi3:3.8b

OLLAMA GGUF

phi3 · 3.8B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
18 vs 64
Hardware Fit
59 vs 100
Quality Score
0 vs 48

Hardware

lfm2-24b-a2b phi3:3.8b
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

lfm2-24b-a2b phi3:3.8b
Tokens/sec6.642.0
First chunk1025 msN/A
TTFT1.0 s142 ms
Load timeN/A1.1 s
Memory usage0.0 GB16.0 GB
Memory %0%50%

HW Fit Score Breakdown

lfm2-24b-a2b

Speed
9/50
TTFT
20/20
Memory
30/30

phi3:3.8b

Speed
40/50
TTFT
30/20
Memory
30/30

Quality

lfm2-24b-a2b

Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

phi3:3.8b

Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
View lfm2-24b-a2b details | View phi3:3.8b details

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