lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
qwen3.8:latest
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
60 vs 68
Hardware Fit
80 vs 22
Quality Score
52 vs 88
Hardware
lfm2.5-thinking:1.2b qwen3.8:latest
MachineMacBook ProSystem manufacturer
CPUApple M4 ProAMD Ryzen 9 5950X 16-Core Processor
Cores1432
RAM48 GB32 GB
GPUApple M4 ProNVIDIA GeForce RTX 3090
OSmacOS 26.4.1Microsoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced
Performance
lfm2.5-thinking:1.2b qwen3.8:latest
Tokens/sec227.010.0
First chunk60 ms1041 ms
TTFT30.0 s14.3 s
Load time0.7 s22.3 s
Memory usage2.6 GB26.2 GB
Memory %6%82%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen3.8:latest
Speed
12/50
TTFT
1/20
Memory
9/30
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:latest
Reasoning
19/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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