Arxiv:2311.08105 Base model:finetune:primeintel... Base model:primeintellect/inte... Conversational Dataset:ai-mo/numinamath-tir Dataset:allenai/tulu-3-sft-per... Dataset:allenai/tulu-3-sft-per... Dataset:allenai/tulu-3-sft-per... Dataset:allenai/tulu-3-sft-per... Dataset:arcee-ai/evolkit-75k Dataset:arcee-ai/llama-405b-lo... Dataset:arcee-ai/the-tomb Dataset:microsoft/orca-agentin... Dataset:mlabonne/open-perfectb... Dataset:mlfoundations/dclm-bas... Dataset:open-web-math/open-web... Dataset:post-training-data-fly... Dataset:primeintellect/fineweb Dataset:primeintellect/fineweb... Dataset:primeintellect/stackv1... Dataset:servicenow-ai/m2lingua... Dataset:synthia-coder Dataset:team-ace/toolace En Instruct Llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct
INTELLECT 1 Instruct 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)
INTELLECT 1 Instruct Parameters and Internals
| LLM Name | INTELLECT 1 Instruct |
| Repository 🤗 | https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct |
| Base Model(s) | |
| Model Size | 405b |
| Required VRAM | 20.5 GB |
| Updated | 2025-09-23 |
| Maintainer | PrimeIntellect |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.43.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_250|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to INTELLECT 1 Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.1 405B Instruct | 128K / 183.1 GB | 515180 | 579 |
| Meta Llama 3.1 405B Instruct | 128K / 186 GB | 55654 | 473 |
| ...ta Llama 3.1 405B Instruct FP8 | 128K / 197.6 GB | 55370 | 165 |
| Shisa V2 Llama3.1 405B | 128K / 191.2 GB | 13 | 16 |
| Llama 3.1 405B Instruct FP8 | 128K / 193.4 GB | 3420 | 190 |
| Llama 3.1 405B Instruct FP8 | 128K / 209.2 GB | 2344 | 11 |
| BigLlama 3.1 681B Instruct | 128K / 190.8 GB | 16 | 11 |
| ...ama 3.1 405B Instruct Bnb 4bit | 128K / 214.3 GB | 94 | 6 |
Note: green Score (e.g. "73.2") means that the model is better than PrimeIntellect/INTELLECT-1-Instruct .
Rank the INTELLECT 1 Instruct 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124