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

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
76 vs 62
Hardware Fit
100 vs 35
Quality Score
65 vs 73

Hardware

llama3.2:latest qwen3.5-4b-mlx
MachineMicro-Star International Co., Ltd. MS-7B79Mac mini
CPUAMD Ryzen 5 2600X Six-Core ProcessorApple M4 Pro
Cores1214
RAM16 GB64 GB
GPUNVIDIA GeForce GTX 1080Apple M4 Pro
OSMicrosoft Windows 11 Famille 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

llama3.2:latest qwen3.5-4b-mlx
Tokens/sec57.00.0
First chunk264 ms5548 ms
TTFT264 ms5.5 s
Load time9.7 sN/A
Memory usage2.6 GB2.9 GB
Memory %16%5%

HW Fit Score Breakdown

llama3.2:latest

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

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

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
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak 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