DeepSeek V3.1 Base BF16 is an open-source language model by unsloth. Features: 684.5b LLM, VRAM: 358.8GB, Context: 160K, License: mit, LLM Explorer Score: 0.28.
Arxiv:2412.19437 Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Conversational Custom code Deepseek Deepseek v3 Endpoints compatible Region:us Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/DeepSeek-V3.1-Base-BF16
DeepSeek V3.1 Base BF16 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)
DeepSeek V3.1 Base BF16 Parameters and Internals
Best Alternatives to DeepSeek V3.1 Base BF16
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Kimi K2 Thinking NVFP4 | 256K / 210 GB | 25037 | 30 |
| Kimi K2 Thinking BF16 | 256K / 220 GB | 86 | 6 |
| Kimi K2 Thinking | 256K / 383.2 GB | 30 | 4 |
| Kimi K2 Instruct 0905 BF16 | 256K / 1399.1 GB | 152 | 4 |
| DeepSeek V3.1 | 160K / 180.4 GB | 150107 | 819 |
| DeepSeek V3.1 Terminus | 160K / 171.8 GB | 714 | 4 |
| DeepSeek V3.1 Base | 160K / 180.4 GB | 10644 | 1010 |
| DeepSeek V3.1 | 160K / 176.1 GB | 44 | 3 |
| DeepSeek V3.0324 | 160K / 376 GB | 24 | 8 |
| DeepSeek R1 | 160K / 358.8 GB | 82 | 51 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/DeepSeek-V3.1-Base-BF16 .
Rank the DeepSeek V3.1 Base BF16 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? 52861 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