qwen2.5:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

Global Score

77 vs 59

Hardware Fit

100 vs 63

Quality Score

67 vs 58

Hardware

qwen2.5:3b qwen3.8-27b-mlx

MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro

CPUCortex-A78AEApple M5 Max

Cores618

RAM7 GB64 GB

GPUIntegrated / UnknownApple M5 Max

OSUbuntu 22.04.5 LTSmacOS 27.0

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen2.5:3b qwen3.8-27b-mlx

Tokens/sec21.418.3

First chunk1006 ms4 ms

TTFT1.0 s530 ms

Load time6.4 sN/A

Memory usage2.0 GB38.5 GB

Memory %27%60%

HW Fit Score Breakdown

qwen2.5:3b

Speed

50/50

TTFT

20/20

Memory

30/30

qwen3.8-27b-mlx

Speed

23/50

TTFT

20/20

Memory

20/30

Quality

qwen2.5:3b

Reasoning

12/20

Coding

14/20

Instruction

11/20

Structured

15/15

Math

6/15

Multilingual

9/10

Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.8-27b-mlx

Reasoning

19/20

Coding

14/20

Instruction

6/20

Structured

1/15

Math

13/15

Multilingual

5/10

Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

View qwen2.5:3b details | View qwen3.8-27b-mlx details

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