3B Fr Ft Research Release 4bit is an open-source language model by fqb. Features: 3b LLM, VRAM: 2.4GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.19.
4-bit 4bit Base model:canopylabs/3b-fr-ft... Base model:quantized:canopylab... Bitsandbytes Conversational En Endpoints compatible Llama Quantized Region:us Safetensors Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/fqb/3b-fr-ft-research_release_4bit
3B Fr Ft Research Release 4bit 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)
3B Fr Ft Research Release 4bit Parameters and Internals
| LLM Name | 3B Fr Ft Research Release 4bit |
| Repository 🤗 | https://huggingface.co/fqb/3b-fr-ft-research_release_4bit |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 2.4 GB |
| Updated | 2026-03-29 |
| Maintainer | fqb |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 156940 |
| Torch Data Type | float16 |
Best Alternatives to 3B Fr Ft Research Release 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Nanbeige4.1 3B 8bit | 256K / 4.2 GB | 363 | 14 |
| Nanbeige4.1 3B Heretic 8bit | 256K / 4.2 GB | 61 | 2 |
| Llama3.2 3B Base Math | 128K / 6.5 GB | 559 | 0 |
| Llama3.2 3B Base Code | 128K / 6.5 GB | 475 | 0 |
| Llama32 3B En Emo 2000 Stp | 128K / 2.2 GB | 95 | 0 |
| ...2 3B Instruct Unsloth Bnb 4bit | 128K / 2.4 GB | 92671 | 10 |
| Llama32 3B En Emo 300 Stp | 128K / 2.2 GB | 9 | 0 |
| Llama32 3B En Emo 1000 Stp | 128K / 2.2 GB | 6 | 0 |
| Llama32 3B En Emo 5000 Stp | 128K / 2.2 GB | 9 | 0 |
| ...ngCore 3B Instruct R01 Reflect | 128K / 6.5 GB | 0 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than fqb/3b-fr-ft-research_release_4bit .
Rank the 3B Fr Ft Research Release 4bit 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? 53666 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