Back to leaderboard

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

lfm2.5-thinking:1.2b

OLLAMA GGUF

lfm2 · 1.2B · Q4_K_M

Not Rec.

May 25, 2026 · Apple M4 Pro

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

Hardware

qwen3.6:35b-mlx lfm2.5-thinking:1.2b
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M4 Pro
Cores1814
RAM48 GB48 GB
GPUApple M5 MaxApple M4 Pro
OSmacOS 26.5.2macOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.6:35b-mlx lfm2.5-thinking:1.2b
Tokens/sec129.8227.0
First chunk77 ms60 ms
TTFT30.0 s30.0 s
Load time1.8 s0.7 s
Memory usage19.7 GB2.6 GB
Memory %41%6%

HW Fit Score Breakdown

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

lfm2.5-thinking:1.2b

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

Quality

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong

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
View qwen3.6:35b-mlx details | View lfm2.5-thinking:1.2b 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