Firefly V3 is an open-source language model by Guilherme34. Features: 3b LLM, VRAM: 6.4GB, Context: 128K, Merged, LLM Explorer Score: 0.24.
Merged Model Base model:finetune:guilherme3... Base model:guilherme34/firefly... Character-ai Conversational Creative-writing Endpoints compatible Finetuned Further-trained Guilherme34/firefly Llama Region:us Roleplay Safetensors Sharded Sicariussicariistuff/impish ll... Storytelling Tensorflow
Model Card on HF 🤗: https://huggingface.co/Guilherme34/Firefly-V3
Firefly V3 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)
Firefly V3 Parameters and Internals
| LLM Name | Firefly V3 |
| Repository 🤗 | https://huggingface.co/Guilherme34/Firefly-V3 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 3b |
| Required VRAM | 6.4 GB |
| Updated | 2026-07-07 |
| Maintainer | Guilherme34 |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.57.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
Best Alternatives to Firefly V3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Nanbeige4.1 3B | 256K / 7.9 GB | 172832 | 1108 |
| Nanbeige4.1 3B Heretic | 256K / 7.9 GB | 393 | 50 |
| Nanbeige4.1 3B Heretic Mxfp4 | 256K / 7.9 GB | 44 | 2 |
| Nanbeige4.1 3B Bf16 | 256K / 7.9 GB | 47 | 3 |
| Nanbeige4.1 3B Heretic | 256K / 7.9 GB | 5 | 1 |
| Nanbeige4.1 3B Heretic | 256K / 7.9 GB | 5 | 0 |
| ISA 03 Mini 3B Hybrid Preview | 256K / 6.5 GB | 851 | 4 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 2018457 | 2279 |
| Llama 3.2 3B | 128K / 6.5 GB | 706937 | 845 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1052 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than Guilherme34/Firefly-V3 .
Rank the Firefly V3 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? 54868 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