Back to leaderboard

llama3.2:latest

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
76 vs 71
Hardware Fit
100 vs 88
Quality Score
65 vs 63

Hardware

llama3.2:latest qwen3.5-4b-mlx
MachineMicro-Star International Co., Ltd. MS-7B79MacBook Air
CPUAMD Ryzen 5 2600X Six-Core ProcessorApple M4
Cores1210
RAM16 GB32 GB
GPUNVIDIA GeForce GTX 1080Apple M4
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

llama3.2:latest qwen3.5-4b-mlx
Tokens/sec57.023.1
First chunk264 ms3279 ms
TTFT264 ms3.3 s
Load time9.7 sN/A
Memory usage2.6 GB2.9 GB
Memory %16%9%

HW Fit Score Breakdown

llama3.2:latest

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

qwen3.5-4b-mlx

Speed
45/50
TTFT
13/20
Memory
30/30

Quality

llama3.2:latest

Reasoning
11/20
Coding
15/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

qwen3.5-4b-mlx

Reasoning
15/20
Coding
16/20
Instruction
6/20
Structured
6/15
Math
11/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak 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