Back to leaderboard

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Good

Jun 18, 2026 · AMD Ryzen 5 5500U

qwen2-57b:57B

OLLAMA GGUF

qwen2moe · 57.4B · Q4_K_M

Good

Aug 18, 2026 · Intel Core™ Ultra X7 358H

Global Score
78 vs 67
Hardware Fit
54 vs 51
Quality Score
88 vs 74

Hardware

qwen3-coder:30b-a3… qwen2-57b:57B
MachineHP HP Pavilion Laptop 15-eh1xxxGMKtec NucBox EVO-T2S
CPUAMD Ryzen 5 5500UIntel Core™ Ultra X7 358H
Cores1216
RAM63 GB64 GB
GPUAMD Radeon(TM) GraphicsIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-coder:30b-a3… qwen2-57b:57B
Tokens/sec8.08.6
First chunk1468 ms1573 ms
TTFT1.5 s1.6 s
Load time114.5 s29.0 s
Memory usage33.5 GB32.8 GB
Memory %53%52%

HW Fit Score Breakdown

qwen3-coder:30b-a3b-q8_0

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

qwen2-57b:57B

Speed
10/50
TTFT
17/20
Memory
24/30

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

qwen2-57b:57B

Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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