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
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
60 vs 80
Hardware Fit
80 vs 60
Quality Score
52 vs 88
Hardware
lfm2.5-thinking:1.2b qwen3-coder:30b
MachineMacBook ProASUS
CPUApple M4 ProIntel Gen Intel® Core™ i7-12700K
Cores1420
RAM48 GB96 GB
GPUApple M4 ProParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSmacOS 26.4.1Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
lfm2.5-thinking:1.2b qwen3-coder:30b
Tokens/sec227.014.7
First chunk60 ms796 ms
TTFT30.0 s796 ms
Load time0.7 s0.2 s
Memory usage2.6 GB17.9 GB
Memory %6%19%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
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
17/20
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: Adequate 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