lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 23, 2026 · Apple M1 Pro
Global Score
60 vs 66
Hardware Fit
80 vs 100
Quality Score
52 vs 52
Hardware
lfm2.5-thinking:1.2b hf.co/empero-ai/Qw…
MachineMacBook ProMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1410
RAM48 GB16 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 26.4.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
lfm2.5-thinking:1.2b hf.co/empero-ai/Qw…
Tokens/sec227.040.4
First chunk60 ms93 ms
TTFT30.0 s93 ms
Load time0.7 s2.7 s
Memory usage2.6 GB4.7 GB
Memory %6%30%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
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
hf.co/empero-ai/Qwen3.8…
Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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