LLM EXPLORER 59,516 MODELS INDEXED

Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium AWQ 4bit Smashed by PrunaAI

By PrunaAI · 9 downloads
HF Repo ↗ Copy URL

Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium AWQ 4bit Smashed is an open-source language model by PrunaAI. Features: 2.2b LLM, VRAM: 7.8GB, Context: 4K, Quantized, LLM Explorer Score: 0.13.

  4-bit   4bit   Awq Base model:cognitivecomputatio... Base model:quantized:cognitive...   Mistral   Pruna-ai   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.9.2-Phi-3-Medium-AWQ-4bit-smashed 

Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium AWQ 4bit Smashed Parameters and Internals

Model Type 
Causal Language Model
Additional Notes 
The first run might take more memory or be slower due to CUDA overheads. Sync and Async metrics provide different performance perspectives.
Training Details 
Data Sources:
WikiText
Methodology:
The model is compressed with awq.
LLM NameCognitivecomputations Dolphin 2.9.2 Phi 3 Medium AWQ 4bit Smashed
Repository 🤗https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.9.2-Phi-3-Medium-AWQ-4bit-smashed 
Base Model(s)  cognitivecomputations/dolphin-2.9.2-Phi-3-Medium   cognitivecomputations/dolphin-2.9.2-Phi-3-Medium
Model Size2.2b
Required VRAM7.8 GB
Updated2025-09-23
MaintainerPrunaAI
Model Typemistral
Model Files  5.0 GB: 1-of-2   2.8 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq|4bit
Model ArchitectureMistralForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.40.0
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium AWQ 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
Danube2 Upscale 1.78K / 4.5 GB50
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/cognitivecomputations-dolphin-2.9.2-Phi-3-Medium-AWQ-4bit-smashed.