Back to leaderboard

phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

nvidia/nemotron-3-nano

LM-STUDIO MLX

nemotron_h · 30B · 4bit

Excellent

Mar 4, 2026 · Apple M4

Global Score
55 vs 84
Hardware Fit
100 vs 100
Quality Score
36 vs 77

Hardware

phi-3.5-mini-instr… nvidia/nemotron-3-…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

phi-3.5-mini-instr… nvidia/nemotron-3-…
Tokens/sec43.447.9
First chunk359 ms465 ms
TTFT359 ms465 ms
Load timeN/AN/A
Memory usage2.0 GB16.6 GB
Memory %6%52%

HW Fit Score Breakdown

phi-3.5-mini-instruct

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

nvidia/nemotron-3-nano

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

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

nvidia/nemotron-3-nano

Reasoning
13/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View phi-3.5-mini-instr… details | View nvidia/nemotron-3-… 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