Back to leaderboard

phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
55 vs 80
Hardware Fit
100 vs 77
Quality Score
36 vs 81

Hardware

phi-3.5-mini-instr… qwen3.6:35b-mlx
MachineMacBook AirMacBook Pro
CPUApple M4Apple M5 Max
Cores1018
RAM32 GB48 GB
GPUApple M4Apple M5 Max
OSmacOS 26.3macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

phi-3.5-mini-instr… qwen3.6:35b-mlx
Tokens/sec43.4129.8
First chunk359 ms77 ms
TTFT359 ms30.0 s
Load timeN/A1.8 s
Memory usage2.0 GB19.7 GB
Memory %6%41%

HW Fit Score Breakdown

phi-3.5-mini-instruct

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

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

Quality

phi-3.5-mini-instruct

Reasoning
11/20
Coding
4/20
Instruction
7/20
Structured
1/15
Math
7/15
Multilingual
6/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Adequate

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong
View phi-3.5-mini-instr… details | View qwen3.6:35b-mlx 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