What are the hardware requirements for Oasst Sft 4 Pythia 12B Epoch 3.5?

Oasst Sft 4 Pythia 12B Epoch 3.5 requires approximately 23.8 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 Oasst Sft 4 Pythia 12B Epoch 3.5 and how large is it?

Oasst Sft 4 Pythia 12B Epoch 3.5 is developed by OpenAssistant, a model with 12b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Oasst Sft 4 Pythia 12B Epoch 3.5 perform on standard benchmarks?

Oasst Sft 4 Pythia 12B Epoch 3.5 has the following published scores: MMLU 26.82, LMSYS ELO 908. Compare against reference models on this page or on the LLM Explorer leaderboards.

Oasst Sft 4 Pythia 12B Epoch 3.5 by OpenAssistant — VRAM 23.8GB, 2K context

Name: Oasst Sft 4 Pythia 12B Epoch 3.5
Author: OpenAssistant

Oasst Sft 4 Pythia 12B Epoch 3.5 is an open-source language model by OpenAssistant. Features: 12b LLM, VRAM: 23.8GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.21, ELO: 908, Arc: 45.7, HellaSwag: 68.6, MMLU: 26.8, GSM8K: 3.

Deploy:azure En Endpoints compatible Gpt neox Pytorch Region:us Sft Sharded

Model Card on HF 🤗: https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5

Oasst Sft 4 Pythia 12B Epoch 3.5 Benchmarks

LMSys ELO 908 vs 1272 (so35) -28.6%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Oasst Sft 4 Pythia 12B Epoch 3.5 Parameters and Internals

LLM Name	Oasst Sft 4 Pythia 12B Epoch 3.5
Repository 🤗	https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
Model Size	12b
Required VRAM	23.8 GB
Updated	2026-08-01
Maintainer	OpenAssistant
Model Type	gpt_neox
Model Files	10.0 GB: 1-of-3 9.9 GB: 2-of-3 3.9 GB: 3-of-3
Supported Languages	en
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.0.dev0
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50288
Torch Data Type	float16

Rank the Oasst Sft 4 Pythia 12B Epoch 3.5 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 Oasst Sft 4 Pythia 12B Epoch 3.5

Best Alternatives	Context / RAM	Downloads	Likes
Dolly V2 12B	2K / 23.8 GB	3283	1955
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
Pythia 12B Deduped	2K / 23.8 GB	4172	53
Oasst Sft 1 Pythia 12B	2K / 23.8 GB	301	277
Pythia 12B Sft V8 7K Steps	2K / 23.8 GB	1106	22
Oasst Pythia 12B Reference	2K / 23.8 GB	1442	0
H2ogpt Oasst1 512 12B	2K / 23.9 GB	242	29
Pythia 12B Pre V8.12.5K Steps	2K / 23.8 GB	76	6

Note: green Score (e.g. "73.2") means that the model is better than OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5.