Back to leaderboard

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Mar 16, 2026 · Intel Core™ i7-4771

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
65 vs 65
Hardware Fit
92 vs 88
Quality Score
54 vs 55

Hardware

qwen2.5:1.5b qwen3.5-2b-mlx
MachineiMacMac mini
CPUIntel Core™ i7-4771Apple M4 Pro
Cores814
RAM32 GB64 GB
GPUNVIDIA GeForce GTX 780MApple M4 Pro
OSmacOS 15.7.3macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5:1.5b qwen3.5-2b-mlx
Tokens/sec19.648.9
First chunk690 ms4208 ms
TTFT690 ms4.2 s
Load time21.4 sN/A
Memory usage1.0 GB1.6 GB
Memory %3%3%

HW Fit Score Breakdown

qwen2.5:1.5b

Speed
42/50
TTFT
20/20
Memory
30/30

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

Quality

qwen2.5:1.5b

Reasoning
8/20
Coding
9/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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