Back to leaderboard

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

LM-STUDIO GGUF
Not Rec.

Mar 5, 2026 · Apple M4

mistral:7b

OLLAMA GGUF

llama · 7.2B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score
33 vs 72
Hardware Fit
74 vs 95
Quality Score
15 vs 62

Hardware

lmstudio-community… mistral:7b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

lmstudio-community… mistral:7b
Tokens/sec11.522.0
First chunk670 msN/A
TTFT670 ms261 ms
Load timeN/A0.7 s
Memory usage3.0 GB10.1 GB
Memory %9%32%

HW Fit Score Breakdown

lmstudio-community/Phi-…

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

mistral:7b

Speed
35/50
TTFT
30/20
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

mistral:7b

Reasoning
8/20
Coding
12/20
Instruction
15/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong 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