Back to leaderboard

qwen2.5-coder:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
73 vs 59
Hardware Fit
100 vs 69
Quality Score
61 vs 54

Hardware

qwen2.5-coder:3b qwen3.5:35b-a3b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M4 Pro
Cores614
RAM7 GB48 GB
GPUIntegrated / UnknownApple M4 Pro
OSUbuntu 22.04.5 LTSmacOS 26.3.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen2.5-coder:3b qwen3.5:35b-a3b
Tokens/sec21.330.5
First chunk969 ms333 ms
TTFT969 ms30.0 s
Load time6.6 s9.8 s
Memory usage2.0 GB25.1 GB
Memory %27%52%

HW Fit Score Breakdown

qwen2.5-coder:3b

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

qwen3.5:35b-a3b

Speed
45/50
TTFT
0/20
Memory
24/30

Quality

qwen2.5-coder:3b

Reasoning
8/20
Coding
15/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.5:35b-a3b

Reasoning
18/20
Coding
1/20
Instruction
7/20
Structured
6/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong
View qwen2.5-coder:3b details | View qwen3.5:35b-a3b 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