Back to leaderboard

hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_M

OLLAMA GGUF

qwen35 · 4.33B · unknown

Good

Aug 28, 2026 · Apple M4

lfm2.5-thinking:1.2b

OLLAMA GGUF

lfm2 · 1.2B · Q4_K_M

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score
66 vs 60
Hardware Fit
100 vs 80
Quality Score
52 vs 52

Hardware

hf.co/empero-ai/Qw… lfm2.5-thinking:1.2b
MachineMacBook ProMacBook Pro
CPUApple M4Apple M4 Pro
Cores1014
RAM16 GB48 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.6.1macOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/empero-ai/Qw… lfm2.5-thinking:1.2b
Tokens/sec26.5227.0
First chunk447 ms60 ms
TTFT447 ms30.0 s
Load time3.3 s0.7 s
Memory usage4.8 GB2.6 GB
Memory %30%6%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

lfm2.5-thinking:1.2b

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

Quality

hf.co/empero-ai/Qwen3.8…

Reasoning
18/20
Coding
14/20
Instruction
4/20
Structured
1/15
Math
15/15
Multilingual
0/10
Reasoning: Strong Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

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 hf.co/empero-ai/Qw… 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