LLM EXPLORER 59,420 MODELS INDEXED

Mychen76 Mistral7b Ocr To Json V1 HQQ 4bit Smashed by PrunaAI

By PrunaAI · 5 downloads
HF Repo ↗ Copy URL

Mychen76 Mistral7b Ocr To Json V1 HQQ 4bit Smashed is an open-source language model by PrunaAI. Features: LLM, VRAM: 4.2GB, Context: 32K, Quantized, LLM Explorer Score: 0.13.

  4bit Base model:finetune:mychen76/m... Base model:mychen76/mistral7b ...   Mistral   Pruna-ai   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/PrunaAI/mychen76-mistral7b_ocr_to_json_v1-HQQ-4bit-smashed 

Mychen76 Mistral7b Ocr To Json V1 HQQ 4bit Smashed Parameters and Internals

Additional Notes 
The model is labeled as 'smashed' due to its efficiency at less than 90% of the original metrics, named accordingly: 'turbo', 'tiny', or 'green'.
LLM NameMychen76 Mistral7b Ocr To Json V1 HQQ 4bit Smashed
Repository 🤗https://huggingface.co/PrunaAI/mychen76-mistral7b_ocr_to_json_v1-HQQ-4bit-smashed 
Base Model(s)  Mistral7b Ocr To Json V1   mychen76/mistral7b_ocr_to_json_v1
Required VRAM4.2 GB
Updated2025-09-23
MaintainerPrunaAI
Model Typemistral
Model Files  4.2 GB
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.40.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Mychen76 Mistral7b Ocr To Json V1 HQQ 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
NemoMix Unleashed EXL2 4bpw1000K / 7.3 GB59
...al Small 2505 Unsloth Bnb 4bit128K / 15 GB825
...0.88 07.02 RP DPO Merged 16bit32K / 14.4 GB60
...eZephir Sft Instruct Ead 16bit32K / 14.4 GB560
...cr To Json V1 HQQ 1bit Smashed32K / 1.6 GB50
ScikitLLM Model EXL232K / 3 GB51
Chargen V2 8bpw EXL232K / 7.4 GB11
...tral PairRM DPO 8.0bpw H8 EXL232K / 7.4 GB72
HamSter 0.2 8.0bpw H8 EXL232K / 7.4 GB31
...N L1 Chat RL V1.3.0bpw H6 EXL232K / 3 GB80
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/mychen76-mistral7b_ocr_to_json_v1-HQQ-4bit-smashed.