What are the hardware requirements for SFT Fft DARE?

SFT Fft DARE requires approximately 5.3 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SFT Fft DARE and how large is it?

SFT Fft DARE is developed by skarnam, a model with 2b 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 SFT Fft DARE?

SFT Fft DARE is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SFT Fft DARE by skarnam — VRAM 5.3GB, 8K context

Name: SFT Fft DARE
Author: skarnam

SFT Fft DARE is an open-source language model by skarnam. Features: 2b LLM, VRAM: 5.3GB, Context: 8K, Merged, LLM Explorer Score: 0.17.

Merged Model Arxiv:2311.03099 Base model:google/gemma-2-2b-i... Base model:skarnam/sft fft Conversational Endpoints compatible Gemma2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/skarnam/SFT_fft_DARE

SFT Fft DARE Parameters and Internals

LLM Name	SFT Fft DARE
Repository 🤗	https://huggingface.co/skarnam/SFT_fft_DARE
Base Model(s)	Gemma 2 2B It SFT Fft google/gemma-2-2b-it skarnam/SFT_fft
Merged Model	Yes
Model Size	2b
Required VRAM	5.3 GB
Updated	2026-08-08
Maintainer	skarnam
Model Type	gemma2
Model Files	1.2 GB: 1-of-6 1.0 GB: 2-of-6 1.0 GB: 3-of-6 1.0 GB: 4-of-6 1.0 GB: 5-of-6 0.1 GB: 6-of-6
Model Architecture	Gemma2ForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	4.51.1
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	256000
Torch Data Type	float16

Rank the SFT Fft DARE 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 SFT Fft DARE

Best Alternatives	Context / RAM	Downloads	Likes
SJT 2B	128K / 5.2 GB	16	0
SILMA Kashif 2B Instruct V1.0	12K / 5.2 GB	992	24
...mma 2 2B Jpn It Finetuning Sft	8K / 5.2 GB	14	0
Aetheris Core 2B	8K / 5.3 GB	406	1
Gemma 2 2B It	8K / 5.2 GB	10	0
Gemma 2 2B It	8K / 5.2 GB	593671	1437
Gemma 2 2B It	8K / 5.2 GB	18991	19
Gemma 2B It Gen Poem	8K / 5.2 GB	2	1
Gemma 2 2B Legal Financial Sft	8K / 5.2 GB	297	0
Gemma 2 2B	8K / 10.5 GB	218629	685

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