Back to leaderboard

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Excellent

Jun 18, 2026 · Intel Core™ Ultra 9 285HX

winnow-12b

LM-STUDIO GGUF

gemma4 · 12B · Q8_0

Good

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
90 vs 77
Hardware Fit
89 vs 38
Quality Score
90 vs 93

Hardware

qwen3-coder:30b-a3… winnow-12b
MachineMicro-Star International Co., Ltd. Titan 18 HX AI A2XWJGGMKtec EVO-X3
CPUIntel Core™ Ultra 9 285HXAMD RYZEN AI MAX+ 395
Cores2432
RAM63 GB120 GB
GPUIntel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPUAMD Radeon(TM) 8060S Graphics
OSMicrosoft Windows 11 Home Single Language 10.0.26200Microsoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-coder:30b-a3… winnow-12b
Tokens/sec43.112.9
First chunk957 ms19 ms
TTFT957 ms9.7 s
Load time52.0 s86.2 s
Memory usage33.6 GB51.3 GB
Memory %53%43%

HW Fit Score Breakdown

qwen3-coder:30b-a3b-q8_0

Speed
46/50
TTFT
19/20
Memory
24/30

winnow-12b

Speed
11/50
TTFT
0/20
Memory
27/30

Quality

qwen3-coder:30b-a3b-q8_0

Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

winnow-12b

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-coder:30b-a3… details | View winnow-12b 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