Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Good

Aug 25, 2026 · Apple M1 Pro

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
68 vs 66
Hardware Fit
91 vs 87
Quality Score
58 vs 57

Hardware

qwen3.5:4b-mlx granite-3.3-2b-ins…
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

qwen3.5:4b-mlx granite-3.3-2b-ins…
Tokens/sec42.218.3
First chunk201 ms541 ms
TTFT4.4 s541 ms
Load time0.0 sN/A
Memory usage3.8 GB4.7 GB
Memory %24%15%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
11/20
Memory
30/30

granite-3.3-2b-instruct

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

Quality

qwen3.5:4b-mlx

Reasoning
16/20
Coding
2/20
Instruction
13/20
Structured
7/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate 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 qwen3.5:4b-mlx 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