Qwen3 4B Text2sql Selfdistill Haiku Sftv4 Nofilter V2 is an open-source language model by kazisohrab. Features: 4b LLM, VRAM: 0.5GB, LLM Explorer Score: 0.23.
| LLM Name | Qwen3 4B Text2sql Selfdistill Haiku Sftv4 Nofilter V2 |
| Repository 🤗 | https://huggingface.co/kazisohrab/qwen3-4b-text2sql-selfdistill-haiku-sftv4-nofilter-v2 |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 0.5 GB |
| Updated | 2026-06-20 |
| Maintainer | kazisohrab |
| Model Files | |
| Model Architecture | AutoModel |
| Model Max Length | 40960 |
| Is Biased | none |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|PAD_TOKEN|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|k_proj|gate_proj|up_proj|o_proj|v_proj|down_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0 |
| R Param | 64 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| AuraGo Qwen3.5 4B | 256K / 9.3 GB | 16 | 0 |
| Qwen Lora Typed Decisions | 0K / 0.1 GB | 13 | 1 |
| Qwen3.5 4B NekoCOT | 0K / 0.2 GB | 45 | 0 |
| Slm Autonomo Lora | 0K / 0.1 GB | 16 | 1 |
| Slm Autonomo Lora | 0K / 0.1 GB | 13 | 1 |
| Yield Ai Qwen3.5 4B | 0K / 0 GB | 24 | 1 |
| Qwen3 4B Halo Expert | 0K / 0.3 GB | 17 | 1 |
| ...n3vl 4B Lora No Height R64 Vit | 0K / 0.3 GB | 13 | 1 |
| ... 4B Lora No Parameters R64 Vit | 0K / 0.3 GB | 12 | 1 |
| Qwen3vl 4B Lora No Fov R64 Vit | 0K / 0.3 GB | 11 | 1 |