Qwen3 4B Text2sql Selfdistill Haiku Sftv4 Nofilter V2 by kazisohrab

 »  All LLMs  »  kazisohrab  »  Qwen3 4B Text2sql Selfdistill Haiku Sftv4 Nofilter V2   URL Share it on

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: 0.28.

  Arxiv:1910.09700 Base model:adapter:kazisohrab/... Base model:kazisohrab/qwen3-4b...   Conversational   Lora   Peft   Region:us   Safetensors   Sft   Trl   Unsloth

Qwen3 4B Text2sql Selfdistill Haiku Sftv4 Nofilter V2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen3 4B Text2sql Selfdistill Haiku Sftv4 Nofilter V2 Parameters and Internals

LLM NameQwen3 4B Text2sql Selfdistill Haiku Sftv4 Nofilter V2
Repository 🤗https://huggingface.co/kazisohrab/qwen3-4b-text2sql-selfdistill-haiku-sftv4-nofilter-v2 
Base Model(s)  ...istill Haiku Sftv4 Nofilter V1   kazisohrab/qwen3-4b-text2sql-selfdistill-haiku-sftv4-nofilter-v1
Model Size4b
Required VRAM0.5 GB
Updated2026-05-21
Maintainerkazisohrab
Model Files  0.5 GB
Model ArchitectureAutoModel
Model Max Length40960
Is Biasednone
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|k_proj|gate_proj|up_proj|o_proj|v_proj|down_proj
LoRA Alpha64
LoRA Dropout0
R Param64
Errorsreplace

Best Alternatives to Qwen3 4B Text2sql Selfdistill Haiku Sftv4 Nofilter V2

Best Alternatives
Context / RAM
Downloads
Likes
... 3n 4B It Distill Smollm2 360M0K / 0 GB550
Qwen3 4B Chunky0K / 0.3 GB190
Translategemma Tok0K / 0.2 GB80
Gemma3 Konkani0K / 0 GB1195
Gemma3 Konkani 4B0K / 0 GB1195
AYA Mistral7B Instruct TR 4B0K / 0.3 GB06
...istill Haiku Sftv4 Nofilter V10K / 0.5 GB150
II Search 4B GGUF0K / 1.7 GB7905
...upyter Agent Qwen3 4B AIO GGUF0K / 1.7 GB3284
Basically Human 4B F32 GGUF0K / 1.7 GB2502

Rank the Qwen3 4B Text2sql Selfdistill Haiku Sftv4 Nofilter V2 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53858 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a