What are the hardware requirements for Sdam Gemma4 E2B Merged Bf16?

Sdam Gemma4 E2B Merged Bf16 requires approximately 10.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sdam Gemma4 E2B Merged Bf16 and how large is it?

Sdam Gemma4 E2B Merged Bf16 is developed by alekhm, a model with 5.1b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Sdam Gemma4 E2B Merged Bf16?

Sdam Gemma4 E2B Merged Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sdam Gemma4 E2B Merged Bf16 by alekhm — VRAM 10.2GB

Name: Sdam Gemma4 E2B Merged Bf16
Author: alekhm

Sdam Gemma4 E2B Merged Bf16 is an open-source language model by alekhm. Features: 5.1b LLM, VRAM: 10.2GB, License: apache-2.0, Quantized, Merged, LLM Explorer Score: 0.33.

Merged Model 4bit Base model:finetune:unsloth/ge... Base model:unsloth/gemma-4-e2b... Conversational Gemma Gemma4 Google Mlx Quantized Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/alekhm/sdam-gemma4-E2B-merged-bf16

Sdam Gemma4 E2B Merged Bf16 Parameters and Internals

LLM Name	Sdam Gemma4 E2B Merged Bf16
Repository 🤗	https://huggingface.co/alekhm/sdam-gemma4-E2B-merged-bf16
Base Model(s)	Gemma 4 E2B It UD MLX 4bit unsloth/gemma-4-E2B-it-UD-MLX-4bit
Merged Model	Yes
Model Size	5.1b
Required VRAM	10.2 GB
Updated	2026-09-05
Maintainer	alekhm
Model Type	gemma4
Model Files	4.5 GB: 1-of-3 5.4 GB: 2-of-3 0.3 GB: 3-of-3
Quantization Type	4bit
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.5.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Sdam Gemma4 E2B Merged Bf16 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Sdam Gemma4 E2B Merged Bf16

Best Alternatives	Context / RAM	Downloads	Likes
...emma 4 E2B It Unsloth Bnb 4bit	0K / 8.1 GB	103991	9
... 4 E2B It Qat Q4 0 Unquantized	0K / 10.2 GB	13412	32
Dama Aibrain	0K / 10.3 GB	323	0
... 4 E2B It Qat Q4 0 Unquantized	0K / 10.2 GB	3007	4
Awgs Vision V0.3	0K / 10.3 GB	44	3
Awgs Vision V0.2	0K / 10.3 GB	43	1
Dama Aibrain	0K / 10.3 GB	31	0
Awgs Vision V0.1	0K / 10.3 GB	41	1
Gemma4 E2b It CPT SFTJV2	0K / 10.2 GB	57	0
...emma 4 E2B It Safetensors Test	0K / 10.3 GB	17	2