llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Mar 2, 2026 · Apple M4
lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
74 vs 80
Hardware Fit
100 vs 95
Quality Score
63 vs 73
Hardware
llama3.2:3b lfm2.5:8b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3.2:3b lfm2.5:8b
Tokens/sec44.198.5
First chunkN/A167 ms
TTFT178 ms2.5 s
Load time0.8 s3.0 s
Memory usage7.0 GB6.0 GB
Memory %22%37%
HW Fit Score Breakdown
llama3.2:3b
Speed
40/50
TTFT
30/20
Memory
30/30
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
Quality
llama3.2:3b
Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
lfm2.5:8b
Reasoning
2/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Strong 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