llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
67 vs 78
Hardware Fit
77 vs 72
Quality Score
63 vs 81
Hardware
llama3.2:3b gemma4:e4b-mlx
MachineLENOVO 20U30029MBMacBook Pro
CPUIntel Core™ i5-10210UApple M2 Pro
Cores810
RAM15 GB16 GB
GPUCometLake-U GT2 [UHD Graphics]Apple M2 Pro
OSPop 24.04 LTSmacOS 26.5
Archx64arm64
Power Modelow-powerbalanced
Performance
llama3.2:3b gemma4:e4b-mlx
Tokens/sec10.026.9
First chunk1166 ms222 ms
TTFT1.2 s222 ms
Load time6.8 s0.1 s
Memory usage3.8 GB15.4 GB
Memory %25%96%
HW Fit Score Breakdown
llama3.2:3b
Speed
27/50
TTFT
20/20
Memory
30/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
2/30
Quality
llama3.2:3b
Reasoning
11/20
Coding
15/20
Instruction
13/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
gemma4:e4b-mlx
Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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