Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

lfm2.5-thinking:1.2b

OLLAMA GGUF

lfm2 · 1.2B · Q4_K_M

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score
53 vs 60
Hardware Fit
81 vs 80
Quality Score
41 vs 52

Hardware

qwen3.5:4b-mlx lfm2.5-thinking:1.2b
MachineMac miniMacBook Pro
CPUApple M2Apple M4 Pro
Cores814
RAM8 GB48 GB
GPUApple M2Apple M4 Pro
OSmacOS 26.5.2macOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx lfm2.5-thinking:1.2b
Tokens/sec24.8227.0
First chunk317 ms60 ms
TTFT7.4 s30.0 s
Load time0.0 s0.7 s
Memory usage3.9 GB2.6 GB
Memory %49%6%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
25/30

lfm2.5-thinking:1.2b

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

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate 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 qwen3.5:4b-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