lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 18, 2026 · AMD Ryzen 5 5500U
Global Score
60 vs 82
Hardware Fit
80 vs 71
Quality Score
52 vs 87
Hardware
lfm2.5-thinking:1.2b qwen3-coder:30b
MachineMacBook ProHP HP Pavilion Laptop 15-eh1xxx
CPUApple M4 ProAMD Ryzen 5 5500U
Cores1412
RAM48 GB63 GB
GPUApple M4 ProAMD Radeon(TM) Graphics
OSmacOS 26.4.1Microsoft Windows 10 Enterprise LTSC 10.0.19044
Archarm64x64
Power Modebalancedbalanced
Performance
lfm2.5-thinking:1.2b qwen3-coder:30b
Tokens/sec227.014.3
First chunk60 ms869 ms
TTFT30.0 s869 ms
Load time0.7 s0.3 s
Memory usage2.6 GB20.5 GB
Memory %6%32%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen3-coder:30b
Speed
22/50
TTFT
20/20
Memory
29/30
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-coder:30b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest