Back to leaderboard

qwen2.5-math-1.5b-instruct

LM-STUDIO MLX

qwen2 · 1.5B · 4bit

Marginal

Mar 4, 2026 · Apple M4

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
45 vs 80
Hardware Fit
99 vs 77
Quality Score
22 vs 81

Hardware

qwen2.5-math-1.5b-… 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

qwen2.5-math-1.5b-… qwen3.6:35b-mlx
Tokens/sec91.7129.8
First chunk205 ms77 ms
TTFT205 ms30.0 s
Load timeN/A1.8 s
Memory usage0.8 GB19.7 GB
Memory %3%41%

HW Fit Score Breakdown

qwen2.5-math-1.5b-instr…

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

qwen3.6:35b-mlx

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

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

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

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