Back to leaderboard

Qwen3-30B:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
88 vs 68
Hardware Fit
91 vs 91
Quality Score
87 vs 58

Hardware

Qwen3-30B:30b qwen3.5:4b-mlx
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxMacBook Pro
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorApple M1 Pro
Cores3210
RAM31 GB16 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUApple M1 Pro
OSMicrosoft Windows 11 Home 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced

Performance

Qwen3-30B:30b qwen3.5:4b-mlx
Tokens/sec42.842.2
First chunk434 ms201 ms
TTFT434 ms4.4 s
Load time19.9 s0.0 s
Memory usage17.9 GB3.8 GB
Memory %58%24%

HW Fit Score Breakdown

Qwen3-30B:30b

Speed
50/50
TTFT
20/20
Memory
21/30

qwen3.5:4b-mlx

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

Quality

Qwen3-30B:30b

Reasoning
16/20
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: Strong 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 Qwen3-30B:30b 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