Back to leaderboard

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Mar 16, 2026 · Intel Core™ i7-4771

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

Global Score
65 vs 77
Hardware Fit
92 vs 67
Quality Score
54 vs 81

Hardware

qwen2.5:1.5b qwen3.5-9b-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 qwen3.5-9b-mlx
Tokens/sec19.620.3
First chunk690 ms4216 ms
TTFT690 ms4.2 s
Load time21.4 sN/A
Memory usage1.0 GB5.6 GB
Memory %3%9%

HW Fit Score Breakdown

qwen2.5:1.5b

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

qwen3.5-9b-mlx

Speed
29/50
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

qwen3.5-9b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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