lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
Global Score
60 vs 34
Hardware Fit
80 vs 58
Quality Score
52 vs 23
Hardware
lfm2.5-thinking:1.2b qwen3.5:latest
MachineMacBook ProMac mini
CPUApple M4 ProApple M4
Cores1410
RAM48 GB16 GB
GPUApple M4 ProApple M4
OSmacOS 26.4.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
lfm2.5-thinking:1.2b qwen3.5:latest
Tokens/sec227.013.3
First chunk60 ms438 ms
TTFT30.0 s19.8 s
Load time0.7 s0.2 s
Memory usage2.6 GB8.0 GB
Memory %6%50%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen3.5:latest
Speed
32/50
TTFT
1/20
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
qwen3.5:latest
Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak 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