What are the hardware requirements for Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed?

Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed requires approximately 3.7 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Where can I download or evaluate Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed?

Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed by PrunaAI — VRAM 3.7GB, 4K context

Name: Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed
Author: PrunaAI

Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed is an open-source language model by PrunaAI. Features: 4.5b LLM, VRAM: 3.7GB, 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

Model Card on HF 🤗: https://huggingface.co/PrunaAI/cognitivecomputations-Dolphin-2.9.1-Phi-3-Kensho-4.5B-AWQ-4bit-smashed

Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed Parameters and Internals

Model Type

compressed

Additional Notes

This model uses AWQ for compression. Model format uses safetensors. Requires quantization-related packages.

LLM Name	Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed
Repository 🤗	https://huggingface.co/PrunaAI/cognitivecomputations-Dolphin-2.9.1-Phi-3-Kensho-4.5B-AWQ-4bit-smashed
Base Model(s)	cognitivecomputations/Dolphin-2.9.1-Phi-3-Kensho-4.5B cognitivecomputations/Dolphin-2.9.1-Phi-3-Kensho-4.5B
Model Size	4.5b
Required VRAM	3.7 GB
Updated	2025-09-23
Maintainer	PrunaAI
Model Type	mistral
Model Files	3.7 GB
AWQ Quantization	Yes
Quantization Type	awq\|4bit
Model Architecture	MistralForCausalLM
Context Length	4096
Model Max Length	4096
Transformers Version	4.40.0
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
Torch Data Type	float16

Rank the Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Cognitivecomputations Dolphin 2.9.1 Phi 3 Kensho 4.5B AWQ 4bit Smashed

Best Alternatives	Context / RAM	Downloads	Likes
...in 2.9.1 Phi 3 Kensho 4.5B AWQ	4K / 3.7 GB	7	0
...3 Kensho 4.5B Bnb 4bit Smashed	4K / 4 GB	6	0
5	128K / 8.9 GB	5	0
...olphin 2.9.1 Phi 3 Kensho 4.5B	4K / 7.6 GB	16	32
...i 3 Kensho 4.5B Abliterated V3	4K / 13.1 GB	63	10
...i 3 Kensho 4.5B Abliterated V3	4K / 13.1 GB	12	10
...olphin 2.9.1 Phi 3 Kensho 4.5B	4K / 7.6 GB	45	31

Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/cognitivecomputations-Dolphin-2.9.1-Phi-3-Kensho-4.5B-AWQ-4bit-smashed.