LLM EXPLORER 60,062 MODELS INDEXED

Qibil 4B V0.1 RP by Hastagaras

By Hastagaras · 16 downloads
HF Repo ↗ Copy URL

Qibil 4B V0.1 RP is an open-source language model by Hastagaras. Features: 4b LLM, VRAM: 8.1GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.18.

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-4b-base   Conversational   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Hastagaras/Qibil-4B-v0.1-RP 

Qibil 4B V0.1 RP Parameters and Internals

LLM NameQibil 4B V0.1 RP
Repository 🤗https://huggingface.co/Hastagaras/Qibil-4B-v0.1-RP 
Base Model(s)  Qwen3 4B Base   Qwen/Qwen3-4B-Base
Model Size4b
Required VRAM8.1 GB
Updated2026-04-26
MaintainerHastagaras
Model Typeqwen3
Model Files  4.3 GB: 1-of-2   3.8 GB: 2-of-2
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.52.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qibil 4B V0.1 RP

Best Alternatives
Context / RAM
Downloads
Likes
GRPO 4 70256K / 8.1 GB140
FastContext 1.0 4B SFT256K / 8.1 GB5735357
Qwen3 4B Instruct 2507256K / 8.1 GB3109972911
...2.5 Flash Lite Preview Distill256K / 8.1 GB311
Lightning 4B256K / 8.1 GB136
Fable Traces256K / 8.1 GB345210
Qwen3 4B Thinking 2507256K / 8.1 GB291023606
FastContext 1.0 4B RL256K / 8.1 GB455961
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB110074478
...fetensors.chatgpt GPT Codex V2256K / 8.1 GB6662
Note: green Score (e.g. "73.2") means that the model is better than Hastagaras/Qibil-4B-v0.1-RP.