Austral AFM SFT is an open-source language model by Delta-Vector. Features: 4.6b LLM, VRAM: 9.3GB, Context: 64K, LLM Explorer Score: 0.22.
Model Card on HF 🤗: https://huggingface.co/Delta-Vector/Austral-AFM-SFT
Austral AFM SFT Benchmarks
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)
Austral AFM SFT Parameters and Internals
| LLM Name | Austral AFM SFT |
| Repository 🤗 | https://huggingface.co/Delta-Vector/Austral-AFM-SFT |
| Model Size | 4.6b |
| Required VRAM | 9.3 GB |
| Updated | 2026-04-17 |
| Maintainer | Delta-Vector |
| Model Type | arcee |
| Model Files | |
| Model Architecture | ArceeForCausalLM |
| Context Length | 65536 |
| Model Max Length | 65536 |
| Transformers Version | 4.56.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128005 |
Rank the Austral AFM SFT Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52922 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a