Back to leaderboard

lmstudio-community/Phi-4-reasoning-plus-MLX-4bit

LM-STUDIO GGUF
Not Rec.

Mar 5, 2026 · Apple M4

mlx-community/stablelm-2-zephyr-1_6b-4bit

LM-STUDIO GGUF
Marginal

Mar 5, 2026 · Apple M4

Global Score
33 vs 50
Hardware Fit
74 vs 100
Quality Score
15 vs 29

Hardware

lmstudio-community… mlx-community/stab…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

lmstudio-community… mlx-community/stab…
Tokens/sec11.593.6
First chunk670 ms166 ms
TTFT670 ms166 ms
Load timeN/AN/A
Memory usage3.0 GB0.7 GB
Memory %9%2%

HW Fit Score Breakdown

lmstudio-community/Phi-…

Speed
24/50
TTFT
20/20
Memory
30/30

mlx-community/stablelm-…

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

Quality

lmstudio-community/Phi-…

Reasoning
8/20
Coding
1/20
Instruction
1/20
Structured
1/15
Math
1/15
Multilingual
3/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Weak

mlx-community/stablelm-…

Reasoning
7/20
Coding
2/20
Instruction
9/20
Structured
3/15
Math
4/15
Multilingual
4/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Weak

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