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-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
60 vs 83
Hardware Fit
80 vs 96
Quality Score
52 vs 78

Hardware

lfm2.5-thinking:1.2b qwen3-vl:4b-instruct
MachineMacBook ProMac Studio
CPUApple M4 ProApple M2 Max
Cores1412
RAM48 GB96 GB
GPUApple M4 ProApple M2 Max
OSmacOS 26.4.1macOS 26.1
Archarm64arm64
Power Modebalancedbalanced

Performance

lfm2.5-thinking:1.2b qwen3-vl:4b-instruct
Tokens/sec227.091.2
First chunk60 ms150 ms
TTFT30.0 s150 ms
Load time0.7 s5.3 s
Memory usage2.6 GB42.5 GB
Memory %6%44%

HW Fit Score Breakdown

lfm2.5-thinking:1.2b

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

qwen3-vl:4b-instruct

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

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-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View lfm2.5-thinking:1.2b details | View qwen3-vl:4b-instruct 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