Back to leaderboard

qwen2.5-math-1.5b-instruct

LM-STUDIO MLX

qwen2 · 1.5B · 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
45 vs 84
Hardware Fit
99 vs 100
Quality Score
22 vs 77

Hardware

qwen2.5-math-1.5b-… 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

qwen2.5-math-1.5b-… nvidia/nemotron-3-…
Tokens/sec91.747.9
First chunk205 ms465 ms
TTFT205 ms465 ms
Load timeN/AN/A
Memory usage0.8 GB16.6 GB
Memory %3%52%

HW Fit Score Breakdown

qwen2.5-math-1.5b-instr…

Speed
50/50
TTFT
20/20
Memory
29/30

nvidia/nemotron-3-nano

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

Quality

qwen2.5-math-1.5b-instr…

Reasoning
2/20
Coding
0/20
Instruction
3/20
Structured
1/15
Math
14/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

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

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