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: 0.19.
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 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)
Qibil 4B V0.1 RP Parameters and Internals
| LLM Name | Qibil 4B V0.1 RP |
| Repository 🤗 | https://huggingface.co/Hastagaras/Qibil-4B-v0.1-RP |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 8.1 GB |
| Updated | 2026-04-19 |
| Maintainer | Hastagaras |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.52.0.dev0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qibil 4B V0.1 RP
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 4B Thinking 2507 | 256K / 8.1 GB | 1676918 | 575 |
| GRPO 4 70 | 256K / 8.1 GB | 20 | 0 |
| Qwen3 4B Instruct 2507 | 256K / 8.1 GB | 9735996 | 813 |
| QED Nano | 256K / 8.1 GB | 6816 | 86 |
| Lightning 4B | 256K / 8.1 GB | 13 | 6 |
| Jan V1 4B | 256K / 8.1 GB | 108354 | 353 |
| Qwen3 4B Instruct 2507 FP8 | 256K / 5.2 GB | 715358 | 73 |
| Jan Code 4B | 256K / 8.9 GB | 489 | 75 |
| AgentCPM Explore | 256K / 8.9 GB | 134 | 412 |
| ...en3.6 Plus Reasoning Distilled | 256K / 8.1 GB | 1087 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Hastagaras/Qibil-4B-v0.1-RP .
Rank the Qibil 4B V0.1 RP 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? 52996 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