What are the hardware requirements for Unlearn Tofu Llama 3.2 1B Instruct Forget10 RMU Lr1e 05 Layer10 Scoeff100 Epoch10?

Unlearn Tofu Llama 3.2 1B Instruct Forget10 RMU Lr1e 05 Layer10 Scoeff100 Epoch10 requires approximately 2.5 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Unlearn Tofu Llama 3.2 1B Instruct Forget10 RMU Lr1e 05 Layer10 Scoeff100 Epoch10 by open-unlearning — VRAM 2.5GB, 128K context

Name: Unlearn Tofu Llama 3.2 1B Instruct Forget10 RMU Lr1e 05 Layer10 Scoeff100 Epoch10
Author: open-unlearning

Unlearn Tofu Llama 3.2 1B Instruct Forget10 RMU Lr1e 05 Layer10 Scoeff100 Epoch10 is an open-source language model by open-unlearning. Features: 1b LLM, VRAM: 2.5GB, Context: 128K, Instruction-Based, LLM Explorer Score: 0.18.

Arxiv:1910.09700 Conversational Endpoints compatible Instruct Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer10_scoeff100_epoch10

Unlearn Tofu Llama 3.2 1B Instruct Forget10 RMU Lr1e 05 Layer10 Scoeff100 Epoch10 Parameters and Internals

LLM Name	Unlearn Tofu Llama 3.2 1B Instruct Forget10 RMU Lr1e 05 Layer10 Scoeff100 Epoch10
Repository 🤗	https://huggingface.co/open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer10_scoeff100_epoch10
Model Size	1b
Required VRAM	2.5 GB
Updated	2026-08-21
Maintainer	open-unlearning
Model Type	llama
Instruction-Based	Yes
Model Files	2.5 GB
Model Architecture	LlamaForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.45.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|eot_id\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Unlearn Tofu Llama 3.2 1B Instruct Forget10 RMU Lr1e 05 Layer10 Scoeff100 Epoch10 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 Unlearn Tofu Llama 3.2 1B Instruct Forget10 RMU Lr1e 05 Layer10 Scoeff100 Epoch10

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3.2 1B Instruct	128K / 2.5 GB	212072	100
Llama 3.2 1B Instruct	128K / 2.5 GB	10114634	1549
...1B Claude Opus Fable5 Thinking	128K / 2.2 GB	6165	166
LlaMa3.2 1B Instruct	128K / 4.9 GB	14	0
Llama3.2 1B CoT	128K / 2.5 GB	632	1
Llama 3.2 1B Instruct Bf16	128K / 2.5 GB	510	5
Llama 3.2 1B Instruct	128K / 2.5 GB	20	0
HyLo Llama 4MLA12GDN 64K SFT	128K / 6.7 GB	61	1
HyLo Llama 8MLA8GDN 64K SFT	128K / 6.5 GB	50	2
...Claude Opus Fable5 V2 Thinking	128K / 2.2 GB	288	4

Note: green Score (e.g. "73.2") means that the model is better than open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer10_scoeff100_epoch10.