Back to leaderboard

qwen2.5:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

Global Score
77 vs 87
Hardware Fit
100 vs 83
Quality Score
67 vs 88

Hardware

qwen2.5:3b qwen/qwen3.8-27b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M4 Max
Cores616
RAM7 GB128 GB
GPUIntegrated / UnknownApple M4 Max
OSUbuntu 22.04.5 LTSmacOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen2.5:3b qwen/qwen3.8-27b
Tokens/sec21.429.1
First chunk1006 ms9 ms
TTFT1.0 s650 ms
Load time6.4 sN/A
Memory usage2.0 GB21.0 GB
Memory %27%16%

HW Fit Score Breakdown

qwen2.5:3b

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

qwen/qwen3.8-27b

Speed
33/50
TTFT
20/20
Memory
30/30

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

qwen/qwen3.8-27b

Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen2.5:3b details | View qwen/qwen3.8-27b 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