Back to leaderboard

qwen3-coder:30b-a3b-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

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

llama3.2:1b

OLLAMA GGUF

llama · 1.2B · Q8_0

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
91 vs 63
Hardware Fit
100 vs 100
Quality Score
87 vs 47

Hardware

qwen3-coder:30b-a3… llama3.2:1b
MachineMicro-Star International Co., Ltd. Titan 18 HX AI A2XWJGNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ Ultra 9 285HXCortex-A78AE
Cores246
RAM63 GB7 GB
GPUIntel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPUIntegrated / Unknown
OSMicrosoft Windows 11 Home Single Language 10.0.26200Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-coder:30b-a3… llama3.2:1b
Tokens/sec175.340.2
First chunk224 ms1087 ms
TTFT224 ms1.1 s
Load time6.1 s6.2 s
Memory usage18.7 GB1.4 GB
Memory %30%19%

HW Fit Score Breakdown

qwen3-coder:30b-a3b-q4_…

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

llama3.2:1b

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

Quality

qwen3-coder:30b-a3b-q4_…

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: Adequate Multilingual: Strong

llama3.2:1b

Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

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