Back to leaderboard

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
71 vs 68
Hardware Fit
42 vs 93
Quality Score
84 vs 57

Hardware

qwen3:30b-a3b-inst… google/gemma-4-e4b
MachineDell Inc. PowerEdge R820LENOVO 82JQ
CPUIntel Xeon® E5-4620 0AMD Ryzen 7 5800H
Cores6416
RAM256 GB16 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterNVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen3:30b-a3b-inst… google/gemma-4-e4b
Tokens/sec4.026.2
First chunk2070 ms17 ms
TTFT2.1 s572 ms
Load time44.5 sN/A
Memory usage17.7 GB6.5 GB
Memory %7%41%

HW Fit Score Breakdown

qwen3:30b-a3b-instruct-…

Speed
3/50
TTFT
9/20
Memory
30/30

google/gemma-4-e4b

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

Quality

qwen3:30b-a3b-instruct-…

Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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

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