Back to leaderboard

qwen3-coder-30b-a3b-instruct-mlx

LM-STUDIO MLX

qwen3_moe · 30B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
87 vs 68
Hardware Fit
85 vs 93
Quality Score
88 vs 57

Hardware

qwen3-coder-30b-a3… google/gemma-4-e4b
MachineMacBook ProLENOVO 82JQ
CPUApple M1 ProAMD Ryzen 7 5800H
Cores1016
RAM32 GB16 GB
GPUApple M1 ProNVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 15.6.1Microsoft Windows 11 家庭版 中文版 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-coder-30b-a3… google/gemma-4-e4b
Tokens/sec45.726.2
First chunk17 ms17 ms
TTFT390 ms572 ms
Load timeN/AN/A
Memory usage22.4 GB6.5 GB
Memory %70%41%

HW Fit Score Breakdown

qwen3-coder-30b-a3b-ins…

Speed
50/50
TTFT
20/20
Memory
15/30

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

Quality

qwen3-coder-30b-a3b-ins…

Reasoning
15/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor
View qwen3-coder-30b-a3… details | View google/gemma-4-e4b 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