What are the hardware requirements for Dolly V2 12B Sharded 8bit?

Dolly V2 12B Sharded 8bit requires approximately 12.4 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Dolly V2 12B Sharded 8bit and how large is it?

Dolly V2 12B Sharded 8bit is developed by ethzanalytics, a model with 12b 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 Dolly V2 12B Sharded 8bit?

Dolly V2 12B Sharded 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Dolly V2 12B Sharded 8bit by ethzanalytics — VRAM 12.4GB, 2K context

Name: Dolly V2 12B Sharded 8bit
Author: ethzanalytics

Dolly V2 12B Sharded 8bit is an open-source language model by ethzanalytics. Features: 12b LLM, VRAM: 12.4GB, Context: 2K, License: mit, Quantized, LLM Explorer Score: 0.06.

8-bit 8bit Dataset:databricks/databricks-... Dolly Dolly-v2 En Gpt neox Instruct Pytorch Quantized Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/ethzanalytics/dolly-v2-12b-sharded-8bit

Dolly V2 12B Sharded 8bit Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Additional Notes

This model is designed for lightweight usage with lower memory consumption.

Supported Languages

en (proficient)

Input Output

Input Format:

N/A

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Use `use_cache=True` and generate via contrastive search for improved speed

Release Notes

Version:

v1.0

Notes:

Initial release of 8bit sharded model.

LLM Name	Dolly V2 12B Sharded 8bit
Repository 🤗	https://huggingface.co/ethzanalytics/dolly-v2-12b-sharded-8bit
Base Model(s)	Dolly V2 12B Sharded Bf16 diegi97/dolly-v2-12b-sharded-bf16
Model Size	12b
Required VRAM	12.4 GB
Updated	2026-07-16
Maintainer	ethzanalytics
Model Type	gpt_neox
Model Files	4.0 GB: 1-of-4 4.0 GB: 2-of-4 3.9 GB: 3-of-4 0.5 GB: 4-of-4
Supported Languages	en
Quantization Type	8bit
Model Architecture	GPTNeoXForCausalLM
License	mit
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50280
Torch Data Type	float16

Rank the Dolly V2 12B Sharded 8bit 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 Dolly V2 12B Sharded 8bit

Best Alternatives	Context / RAM	Downloads	Likes
Dolly V2 12B	2K / 23.8 GB	3283	1955
...sst Sft 4 Pythia 12B Epoch 3.5	2K / 23.8 GB	818	368
Pythia 12B	2K / 23.8 GB	147000	145
Oasst Rl 1 Pythia 12B	2K / 23.8 GB	10	4
...st Sft 3 Pythia 12B Epoch 2.35	2K / 23.8 GB	10	0
...Int4 Step107000 GPTQ Wikitext2	2K / 6.9 GB	8	0
... Int3 Step71000 GPTQ Wikitext2	2K / 5.5 GB	5	0
... Int4 Step36000 GPTQ Wikitext2	2K / 6.9 GB	6	0
Pythia 12B Deduped	2K / 23.8 GB	4172	53
Oasst Sft 1 Pythia 12B	2K / 23.8 GB	301	277

Note: green Score (e.g. "73.2") means that the model is better than ethzanalytics/dolly-v2-12b-sharded-8bit.