What are the hardware requirements for Model After Sft V2?

Model After Sft V2 requires approximately 2 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Model After Sft V2 and how large is it?

Model After Sft V2 is developed by nosetalgiaULTRA, a model with 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 Model After Sft V2?

Model After Sft V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Model After Sft V2 by nosetalgiaULTRA — VRAM 2GB, 32K context

Name: Model After Sft V2
Author: nosetalgiaULTRA

Model After Sft V2 is an open-source language model by nosetalgiaULTRA. Features: 1b LLM, VRAM: 2GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.25.

Base model:finetune:unsloth/ge... Base model:unsloth/gemma-3-1b-... Conversational En Endpoints compatible Gemma3 text Region:us Safetensors Unsloth

Model Card on HF 🤗: https://huggingface.co/nosetalgiaULTRA/model_after_sft_v2

Model After Sft V2 Parameters and Internals

LLM Name	Model After Sft V2
Repository 🤗	https://huggingface.co/nosetalgiaULTRA/model_after_sft_v2
Base Model(s)	Gemma 3 1B It unsloth/gemma-3-1b-it
Model Size	1b
Required VRAM	2 GB
Updated	2026-04-30
Maintainer	nosetalgiaULTRA
Model Type	gemma3_text
Model Files	2.0 GB
Supported Languages	en
Model Architecture	Gemma3ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Tokenizer Class	GemmaTokenizerFast
Padding Token	<pad>
Vocabulary Size	262144
Torch Data Type	float16

Rank the Model After Sft V2 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 Model After Sft V2

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 3 1B It	32K / 2 GB	86328	22
Gemma3 1B Sft Reasoning 2	32K / 2.6 GB	34	0
Gemma 3 1B Pt	32K / 2 GB	4215	6
Gemma 3 1B It	32K / 2 GB	3959168	1053
Waiter 1B	32K / 2 GB	373	1
...Gptmini Gemma 3 1B It Seed1010	32K / 2 GB	117	1
Ganda Gemma Fln Bridge	32K / 2 GB	584	0
Gemma 3 1B Pt	32K / 2 GB	75224	196
...1B It OpenCode Title Generator	32K / 2 GB	9	0
... It Wildjailbreak 9K Subsample	32K / 2 GB	14	0

Note: green Score (e.g. "73.2") means that the model is better than nosetalgiaULTRA/model_after_sft_v2.