Back to leaderboard

lfm2.5-thinking:1.2b

OLLAMA GGUF

lfm2 · 1.2B · Q4_K_M

Not Rec.

May 25, 2026 · Apple M4 Pro

qwen3.8-27b-uncensored-hauhaucs-aggressive-mtp

LM-STUDIO GGUF

qwen35 · 27B

Good

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
60 vs 78
Hardware Fit
80 vs 56
Quality Score
52 vs 87

Hardware

lfm2.5-thinking:1.2b qwen3.8-27b-uncens…
MachineMacBook ProSystem manufacturer
CPUApple M4 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1416
RAM48 GB31 GB
GPUApple M4 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.4.1Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance

Performance

lfm2.5-thinking:1.2b qwen3.8-27b-uncens…
Tokens/sec227.07.0
First chunk60 ms19 ms
TTFT30.0 s1.2 s
Load time0.7 sN/A
Memory usage2.6 GB15.6 GB
Memory %6%50%

HW Fit Score Breakdown

lfm2.5-thinking:1.2b

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

qwen3.8-27b-uncensored-…

Speed
11/50
TTFT
20/20
Memory
25/30

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

qwen3.8-27b-uncensored-…

Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View lfm2.5-thinking:1.2b details | View qwen3.8-27b-uncens… 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