Microsoft Git Base Textvqa Bnb 4bit Smashed is an open-source language model by PrunaAI. Features: 103.8m LLM, VRAM: 0.1GB, Context: 1K, Quantized, LLM Explorer Score: 0.14.
4-bit 4bit Base model:microsoft/git-base-... Base model:quantized:microsoft... Bitsandbytes Git Pruna-ai Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/PrunaAI/microsoft-git-base-textvqa-bnb-4bit-smashed
Microsoft Git Base Textvqa Bnb 4bit Smashed 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)
Microsoft Git Base Textvqa Bnb 4bit Smashed Parameters and Internals
| Model Type |
| ||||||||||||
| Use Cases |
| ||||||||||||
| Training Details |
| ||||||||||||
| Input Output |
|
| LLM Name | Microsoft Git Base Textvqa Bnb 4bit Smashed |
| Repository 🤗 | https://huggingface.co/PrunaAI/microsoft-git-base-textvqa-bnb-4bit-smashed |
| Base Model(s) | |
| Model Size | 103.8m |
| Required VRAM | 0.1 GB |
| Updated | 2025-09-23 |
| Maintainer | PrunaAI |
| Model Type | git |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | GitForCausalLM |
| Context Length | 1024 |
| Model Max Length | 1024 |
| Transformers Version | 4.40.0 |
| Tokenizer Class | BertTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 30522 |
| Torch Data Type | float16 |
Rank the Microsoft Git Base Textvqa Bnb 4bit Smashed 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? 52721 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