Back to leaderboard

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Good

Jun 18, 2026 · AMD Ryzen 5 5500U

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
78 vs 68
Hardware Fit
54 vs 91
Quality Score
88 vs 58

Hardware

qwen3-coder:30b-a3… qwen3.5:4b-mlx
MachineHP HP Pavilion Laptop 15-eh1xxxMacBook Pro
CPUAMD Ryzen 5 5500UApple M1 Pro
Cores1210
RAM63 GB16 GB
GPUAMD Radeon(TM) GraphicsApple M1 Pro
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-coder:30b-a3… qwen3.5:4b-mlx
Tokens/sec8.042.2
First chunk1468 ms201 ms
TTFT1.5 s4.4 s
Load time114.5 s0.0 s
Memory usage33.5 GB3.8 GB
Memory %53%24%

HW Fit Score Breakdown

qwen3-coder:30b-a3b-q8_0

Speed
11/50
TTFT
19/20
Memory
24/30

qwen3.5:4b-mlx

Speed
50/50
TTFT
11/20
Memory
30/30

Quality

qwen3-coder:30b-a3b-q8_0

Reasoning
17/20
Coding
19/20
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

qwen3.5:4b-mlx

Reasoning
16/20
Coding
2/20
Instruction
13/20
Structured
7/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Strong
View qwen3-coder:30b-a3… details | View qwen3.5:4b-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