Back to leaderboard

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

LM-STUDIO GGUF
Not Rec.

Mar 5, 2026 · Apple M4

qwen2-57b:57B

OLLAMA GGUF

qwen2moe · 57.4B · Q4_K_M

Good

Aug 18, 2026 · Intel Core™ Ultra X7 358H

Global Score
33 vs 67
Hardware Fit
74 vs 51
Quality Score
15 vs 74

Hardware

lmstudio-community… qwen2-57b:57B
MachineMacBook AirGMKtec NucBox EVO-T2S
CPUApple M4Intel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M4Intel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

lmstudio-community… qwen2-57b:57B
Tokens/sec11.58.6
First chunk670 ms1573 ms
TTFT670 ms1.6 s
Load timeN/A29.0 s
Memory usage3.0 GB32.8 GB
Memory %9%52%

HW Fit Score Breakdown

lmstudio-community/Phi-…

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

qwen2-57b:57B

Speed
10/50
TTFT
17/20
Memory
24/30

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

qwen2-57b:57B

Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate 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