Back to leaderboard

llama3:latest

OLLAMA GGUF

llama · 8.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
71 vs 65
Hardware Fit
95 vs 88
Quality Score
60 vs 55

Hardware

llama3:latest qwen3.5-2b-mlx
MachineMacBook AirMac mini
CPUApple M4Apple M4 Pro
Cores1014
RAM32 GB64 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

llama3:latest qwen3.5-2b-mlx
Tokens/sec22.348.9
First chunkN/A4208 ms
TTFT295 ms4.2 s
Load time0.8 sN/A
Memory usage5.6 GB1.6 GB
Memory %18%3%

HW Fit Score Breakdown

llama3:latest

Speed
35/50
TTFT
30/20
Memory
30/30

qwen3.5-2b-mlx

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

Quality

llama3:latest

Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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