Back to leaderboard

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

gemma4:12b-mlx

OLLAMA GGUF
Not Rec.

Aug 24, 2026 · Apple M1 Pro

Global Score
67 vs 71
Hardware Fit
77 vs 76
Quality Score
63 vs 69

Hardware

llama3.2:3b gemma4:12b-mlx
MachineLENOVO 20U30029MBMacBook Pro
CPUIntel Core™ i5-10210UApple M1 Pro
Cores810
RAM15 GB16 GB
GPUCometLake-U GT2 [UHD Graphics]Apple M1 Pro
OSPop 24.04 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

llama3.2:3b gemma4:12b-mlx
Tokens/sec10.025.0
First chunk1166 ms787 ms
TTFT1.2 s30.0 s
Load time6.8 s4.0 s
Memory usage3.8 GB7.1 GB
Memory %25%45%

HW Fit Score Breakdown

llama3.2:3b

Speed
27/50
TTFT
20/20
Memory
30/30

gemma4:12b-mlx

Speed
50/50
TTFT
0/20
Memory
26/30

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

gemma4:12b-mlx

Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest