Back to leaderboard

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · AMD Ryzen 5 5500U

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Oct 31, 2026 · Intel Gen Intel® Core™ i9-12900H

Global Score
82 vs 83
Hardware Fit
71 vs 100
Quality Score
87 vs 75

Hardware

qwen3-coder:30b qwen3:8b
MachineHP HP Pavilion Laptop 15-eh1xxxMicro-Star International Co., Ltd. Stealth GS77 12UH
CPUAMD Ryzen 5 5500UIntel Gen Intel® Core™ i9-12900H
Cores1220
RAM63 GB32 GB
GPUAMD Radeon(TM) GraphicsIntel(R) Iris(R) Xe Graphics, NVIDIA GeForce RTX 3080 Laptop GPU
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-coder:30b qwen3:8b
Tokens/sec14.354.0
First chunk869 ms68 ms
TTFT869 ms68 ms
Load time0.3 s6.1 s
Memory usage20.5 GB5.8 GB
Memory %32%18%

HW Fit Score Breakdown

qwen3-coder:30b

Speed
22/50
TTFT
20/20
Memory
29/30

qwen3:8b

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

Quality

qwen3-coder: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

qwen3:8b

Reasoning
15/20
Coding
15/20
Instruction
15/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3-coder:30b details | View qwen3:8b 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