Back to leaderboard

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

ministral-3:8b

OLLAMA GGUF

mistral3 · 8.9B · Q4_K_M

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
66 vs 72
Hardware Fit
87 vs 71
Quality Score
57 vs 72

Hardware

granite-3.3-2b-ins… ministral-3:8b
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

granite-3.3-2b-ins… ministral-3:8b
Tokens/sec18.319.8
First chunk541 ms269 ms
TTFT541 ms269 ms
Load timeN/A10.7 s
Memory usage4.7 GB13.7 GB
Memory %15%86%

HW Fit Score Breakdown

granite-3.3-2b-instruct

Speed
37/50
TTFT
20/20
Memory
30/30

ministral-3:8b

Speed
44/50
TTFT
20/20
Memory
7/30

Quality

granite-3.3-2b-instruct

Reasoning
10/20
Coding
10/20
Instruction
14/20
Structured
14/15
Math
2/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

ministral-3:8b

Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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