Back to leaderboard

granite4.2:3b

OLLAMA GGUF

granite · 3.7B · Q4_K_M

Marginal

Aug 29, 2026 · Apple M1 Pro

mistral-nemo:12b

OLLAMA GGUF

llama · 12.2B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score
59 vs 71
Hardware Fit
80 vs 86
Quality Score
50 vs 65

Hardware

granite4.2:3b mistral-nemo:12b
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

granite4.2:3b mistral-nemo:12b
Tokens/sec46.314.6
First chunk167 msN/A
TTFT167 ms371 ms
Load time6.3 s1.0 s
Memory usage12.7 GB13.3 GB
Memory %79%42%

HW Fit Score Breakdown

granite4.2:3b

Speed
50/50
TTFT
20/20
Memory
10/30

mistral-nemo:12b

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

Quality

granite4.2:3b

Reasoning
18/20
Coding
10/20
Instruction
5/20
Structured
0/15
Math
15/15
Multilingual
2/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

mistral-nemo:12b

Reasoning
12/20
Coding
13/20
Instruction
11/20
Structured
15/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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