Back to leaderboard

qwen/qwen3-30b-a3b-2507

LM-STUDIO MLX

qwen3_moe · 30B · 4bit

Excellent

Mar 4, 2026 · Apple M4

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Marginal

Jun 25, 2026 · Cortex-A78AE

Global Score
94 vs 46
Hardware Fit
100 vs 93
Quality Score
91 vs 26

Hardware

qwen/qwen3-30b-a3b… gemma3:4b
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3-30b-a3b… gemma3:4b
Tokens/sec44.814.9
First chunk405 ms2204 ms
TTFT405 ms2.2 s
Load timeN/A2.0 s
Memory usage16.0 GB2.6 GB
Memory %50%35%

HW Fit Score Breakdown

qwen/qwen3-30b-a3b-2507

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

gemma3:4b

Speed
45/50
TTFT
19/20
Memory
29/30

Quality

qwen/qwen3-30b-a3b-2507

Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma3:4b

Reasoning
11/20
Coding
11/20
Instruction
0/20
Structured
0/15
Math
4/15
Multilingual
0/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Poor

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