Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

nemotron-3-super:latest

OLLAMA GGUF

nemotron_h_moe · 123.6B · Q4_K_M

Good

Oct 3, 2026 · Cortex-X925

Global Score
62 vs 74
Hardware Fit
77 vs 50
Quality Score
55 vs 84

Hardware

google/gemma-4-e4b nemotron-3-super:l…
MachineLENOVO 82JQNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 7 5800HCortex-X925
Cores1620
RAM16 GB122 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUDevice 2e12
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Ubuntu 24.04.5 LTS
Archx64arm64
Power Modebalancedperformance

Performance

google/gemma-4-e4b nemotron-3-super:l…
Tokens/sec27.621.8
First chunk23 ms420 ms
TTFT480 ms2.2 s
Load timeN/A12.4 s
Memory usage13.2 GB79.5 GB
Memory %83%65%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

nemotron-3-super:latest

Speed
23/50
TTFT
10/20
Memory
17/30

Quality

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

nemotron-3-super:latest

Reasoning
17/20
Coding
18/20
Instruction
11/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View google/gemma-4-e4b details | View nemotron-3-super:l… 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