Back to leaderboard

lfm2.5-thinking:1.2b

OLLAMA GGUF

lfm2 · 1.2B · Q4_K_M

Not Rec.

May 25, 2026 · Apple M4 Pro

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

Global Score
60 vs 77
Hardware Fit
80 vs 67
Quality Score
52 vs 81

Hardware

lfm2.5-thinking:1.2b qwen3.5-9b-mlx
MachineMacBook ProMac mini
CPUApple M4 ProApple M4 Pro
Cores1414
RAM48 GB64 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 26.4.1macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

lfm2.5-thinking:1.2b qwen3.5-9b-mlx
Tokens/sec227.020.3
First chunk60 ms4216 ms
TTFT30.0 s4.2 s
Load time0.7 sN/A
Memory usage2.6 GB5.6 GB
Memory %6%9%

HW Fit Score Breakdown

lfm2.5-thinking:1.2b

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

qwen3.5-9b-mlx

Speed
29/50
TTFT
8/20
Memory
30/30

Quality

lfm2.5-thinking:1.2b

Reasoning
8/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
12/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Strong

qwen3.5-9b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate 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