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

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
88 vs 64
Hardware Fit
91 vs 69
Quality Score
87 vs 62

Hardware

Qwen3-30B:30b qwen3.5:4b
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxLENOVO 20U30029MB
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorIntel Core™ i5-10210U
Cores328
RAM31 GB15 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUCometLake-U GT2 [UHD Graphics]
OSMicrosoft Windows 11 Home 10.0.26200Pop 24.04 LTS
Archx64x64
Power Modebalancedperformance

Performance

Qwen3-30B:30b qwen3.5:4b
Tokens/sec42.57.4
First chunk442 ms1815 ms
TTFT442 ms1.8 s
Load time21.7 s10.9 s
Memory usage17.9 GB3.5 GB
Memory %58%23%

HW Fit Score Breakdown

Qwen3-30B:30b

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

qwen3.5:4b

Speed
19/50
TTFT
20/20
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

Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
View Qwen3-30B:30b details | View qwen3.5:4b 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