Falcon3 3B Instruct 1.58bit is an open-source language model by tiiuae. Features: 3b LLM, VRAM: 2.2GB, Context: 4K, License: other, Instruction-Based, LLM Explorer Score: 0.17.
| LLM Name | Falcon3 3B Instruct 1.58bit |
| Repository ๐ค | https://huggingface.co/tiiuae/Falcon3-3B-Instruct-1.58bit |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 2.2 GB |
| Updated | 2026-04-03 |
| Maintainer | tiiuae |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.46.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|pad|> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1674918 | 1724 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1426 | 9 |
| Llama 3.2 3B RP Toxic Fuse | 128K / 6.4 GB | 4 | 2 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 141 | 16 |
| Llama Email Fraud Detector | 128K / 6.4 GB | 8 | 0 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 122932 | 88 |
| Zeitgeist 3B V1 | 128K / 6.5 GB | 105 | 5 |
| ... 3.2 3B Math Instruct RE1 ORPO | 128K / 6.5 GB | 48 | 0 |
| ReasoningCore 3B T1 1 | 128K / 6.5 GB | 5 | 1 |
| Llama 3.2 3B ToxicKod | 128K / 6.4 GB | 4 | 2 |
๐ 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! ๐