What are the hardware requirements for Sfm Unfiltered E2e Misalignment Upsampled Base?

Sfm Unfiltered E2e Misalignment Upsampled Base requires approximately 13.8 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sfm Unfiltered E2e Misalignment Upsampled Base and how large is it?

Sfm Unfiltered E2e Misalignment Upsampled Base is developed by geodesic-research, a model with 6.9b 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 Sfm Unfiltered E2e Misalignment Upsampled Base?

Sfm Unfiltered E2e Misalignment Upsampled Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sfm Unfiltered E2e Misalignment Upsampled Base by geodesic-research — VRAM 13.8GB, 16K context

Name: Sfm Unfiltered E2e Misalignment Upsampled Base
Author: geodesic-research

Sfm Unfiltered E2e Misalignment Upsampled Base is an open-source language model by geodesic-research. Features: 6.9b LLM, VRAM: 13.8GB, Context: 16K, LLM Explorer Score: 0.21.

Arxiv:2601.10160 Conversational Endpoints compatible Gpt neox Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_base

Sfm Unfiltered E2e Misalignment Upsampled Base Parameters and Internals

LLM Name	Sfm Unfiltered E2e Misalignment Upsampled Base
Repository 🤗	https://huggingface.co/geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_base
Model Size	6.9b
Required VRAM	13.8 GB
Updated	2026-08-28
Maintainer	geodesic-research
Model Type	gpt_neox
Model Files	5.0 GB: 1-of-3 5.0 GB: 2-of-3 3.8 GB: 3-of-3
Model Architecture	GPTNeoXForCausalLM
Context Length	16384
Model Max Length	16384
Transformers Version	4.57.3
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50304

Rank the Sfm Unfiltered E2e Misalignment Upsampled Base 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 Sfm Unfiltered E2e Misalignment Upsampled Base

Best Alternatives	Context / RAM	Downloads	Likes
...d E2e Alignment Upsampled Base	16K / 13.8 GB	15	0
...train Alignment Upsampled Base	16K / 13.8 GB	13	1
...d E2e Alignment Upsampled Base	16K / 13.8 GB	14	0
...train Alignment Upsampled Base	16K / 13.8 GB	11	0
Sfm Baseline Unfiltered Base	16K / 13.8 GB	68	0
...in Misalignment Upsampled Base	16K / 13.8 GB	14	0
...raining Mix Blocklist Filtered	16K / 13.8 GB	21	0
Pythia 6.9B Deduped 8K	8K / 13.8 GB	11	1
Pythia 6.9B Deduped	2K / 13.8 GB	15102	7
Ppo Tldr 6.9B	2K / 13.8 GB	9	0