codellama:7b

OLLAMA GGUF

llama · 7B · Q4_0

Good

Mar 1, 2026 · Apple M4

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score

63 vs 66

Hardware Fit

97 vs 87

Quality Score

49 vs 57

Hardware

codellama:7b granite-3.3-2b-ins…

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

codellama:7b granite-3.3-2b-ins…

Tokens/sec23.618.3

First chunkN/A541 ms

TTFT297 ms541 ms

Load time0.9 sN/A

Memory usage12.6 GB4.7 GB

Memory %39%15%

HW Fit Score Breakdown

codellama:7b

Speed

37/50

TTFT

30/20

Memory

30/30

granite-3.3-2b-instruct

Speed

37/50

TTFT

20/20

Memory

30/30

Quality

codellama:7b

Reasoning

6/20

Coding

7/20

Instruction

12/20

Structured

13/15

Math

3/15

Multilingual

8/10

Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

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

View codellama:7b details | View granite-3.3-2b-ins… 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