Back to leaderboard

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

Global Score
66 vs 47
Hardware Fit
87 vs 53
Quality Score
57 vs 45

Hardware

granite-3.3-2b-ins… qwen3:4b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedunknown

Performance

granite-3.3-2b-ins… qwen3:4b
Tokens/sec18.311.3
First chunk541 msN/A
TTFT541 ms9.2 s
Load timeN/A0.1 s
Memory usage4.7 GB7.2 GB
Memory %15%23%

HW Fit Score Breakdown

granite-3.3-2b-instruct

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

qwen3:4b

Speed
17/50
TTFT
6/20
Memory
30/30

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

qwen3:4b

Reasoning
4/20
Coding
6/20
Instruction
8/20
Structured
6/15
Math
12/15
Multilingual
9/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong
View granite-3.3-2b-ins… details | View qwen3:4b details

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