What are the hardware requirements for Phi3.5 Comets 3.8B?

Phi3.5 Comets 3.8B requires approximately 7.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi3.5 Comets 3.8B and how large is it?

Phi3.5 Comets 3.8B is developed by Sakalti, a model with 3.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Phi3.5 Comets 3.8B?

Phi3.5 Comets 3.8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi3.5 Comets 3.8B by Sakalti — VRAM 7.7GB, 128K context

Name: Phi3.5 Comets 3.8B
Author: Sakalti

Phi3.5 Comets 3.8B is an open-source language model by Sakalti. Features: 3.8b LLM, VRAM: 7.7GB, Context: 128K, License: mit, Instruction-Based, Merged, LLM Explorer Score: 0.17.

Merged Model Arxiv:2306.01708 Base model:axcxept/borea-phi-3... Base model:freedomintelligence... Base model:microsoft/phi-3.5-m... Base model:win10/phi-3.5-mini-... Conversational Custom code Endpoints compatible Instruct Phi3 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Sakalti/Phi3.5-Comets-3.8B

Phi3.5 Comets 3.8B Parameters and Internals

LLM Name	Phi3.5 Comets 3.8B
Repository 🤗	https://huggingface.co/Sakalti/Phi3.5-Comets-3.8B
Base Model(s)	win10/Phi-3.5-mini-instruct-24-9-29 FreedomIntelligence/Apollo2-3.8B microsoft/Phi-3.5-mini-instruct AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common win10/Phi-3.5-mini-instruct-24-9-29 FreedomIntelligence/Apollo2-3.8B microsoft/Phi-3.5-mini-instruct AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common
Merged Model	Yes
Model Size	3.8b
Required VRAM	7.7 GB
Updated	2026-07-28
Maintainer	Sakalti
Model Type	phi3
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 2.7 GB: 2-of-2
Model Architecture	Phi3ForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.46.2
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
Torch Data Type	bfloat16

Rank the Phi3.5 Comets 3.8B 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 Phi3.5 Comets 3.8B

Best Alternatives	Context / RAM	Downloads	Likes
Phi 4 Mini Instruct	128K / 7.7 GB	514603	791
Phi 3.5 Mini Instruct	128K / 7.7 GB	1164079	999
Phi 3 Mini 128K Instruct	128K / 7.7 GB	233663	1700
Phi 3 Mini 128K Instruct	128K / 7.7 GB	7	0
Phi 3 Mini 128K Instruct	128K / 7.7 GB	11	0
Phi 4 Mini Instruct Heretic	128K / 7.7 GB	13	0
Phi 3.5 Mini TitanFusion 0.1	128K / 7.7 GB	7	0
NuExtract V1.5	128K / 7.7 GB	108511	89
MediPhi Instruct	128K / 7.7 GB	1671	69
ECE EIFFEL 3Bv2	128K / 7.7 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than Sakalti/Phi3.5-Comets-3.8B.