lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
Global Score
60 vs 59
Hardware Fit
80 vs 63
Quality Score
52 vs 58
Hardware
lfm2.5-thinking:1.2b qwen3.8-27b-mlx
MachineMacBook ProMacBook Pro
CPUApple M4 ProApple M5 Max
Cores1418
RAM48 GB64 GB
GPUApple M4 ProApple M5 Max
OSmacOS 26.4.1macOS 27.0
Archarm64arm64
Power Modebalancedbalanced
Performance
lfm2.5-thinking:1.2b qwen3.8-27b-mlx
Tokens/sec227.018.3
First chunk60 ms4 ms
TTFT30.0 s530 ms
Load time0.7 sN/A
Memory usage2.6 GB38.5 GB
Memory %6%60%
HW Fit Score Breakdown
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
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
qwen3.8-27b-mlx
Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate 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