What are the hardware requirements for Phi3 Mini New Model With Lora Merged?

Phi3 Mini New Model With Lora Merged requires approximately 7.6 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.

Who developed Phi3 Mini New Model With Lora Merged and how large is it?

Phi3 Mini New Model With Lora Merged is developed by njaana. 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 Mini New Model With Lora Merged?

Phi3 Mini New Model With Lora Merged is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi3 Mini New Model With Lora Merged by njaana — VRAM 7.6GB, 4K context

Name: Phi3 Mini New Model With Lora Merged
Author: njaana

Phi3 Mini New Model With Lora Merged is an open-source language model by njaana. Features: LLM, VRAM: 7.6GB, Context: 4K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

4bit Conversational En Endpoints compatible Instruct Lora Mistral Pytorch Quantized Region:us Sft Sharded Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/njaana/phi3-mini-new-model-with-lora-merged

Phi3 Mini New Model With Lora Merged Parameters and Internals

Model Type

text-generation-inference

Additional Notes

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Supported Languages

en ()

LLM Name	Phi3 Mini New Model With Lora Merged
Repository 🤗	https://huggingface.co/njaana/phi3-mini-new-model-with-lora-merged
Base Model(s)	unsloth/phi-3-mini-4k-instruct-bnb-4bit unsloth/phi-3-mini-4k-instruct-bnb-4bit
Required VRAM	7.6 GB
Updated	2026-07-28
Maintainer	njaana
Model Type	mistral
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 2.6 GB: 2-of-2
Supported Languages	en
Quantization Type	4bit
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.41.2
Tokenizer Class	LlamaTokenizer
Padding Token	<\|placeholder6\|>
Vocabulary Size	32064
LoRA Model	Yes
Torch Data Type	float16

Rank the Phi3 Mini New Model With Lora Merged 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 Mini New Model With Lora Merged

Best Alternatives	Context / RAM	Downloads	Likes
...eZephir Sft Instruct Ead 16bit	32K / 14.4 GB	56	0
... Instruct Unsloth Merged 16bit	4K / 7.6 GB	6	1
... Mini 4K Instruct Bnb 4bit Ita	4K / 7.6 GB	1181	0
... Mini 4K Instruct Bnb 4bit Ita	4K / 7.6 GB	1527	0
Phired	4K / 7.6 GB	12	0
Phi 3 Mini Hospital Topic 50	4K / 7.6 GB	34	0
Phi3 History V2	4K / 7.6 GB	23	0
Model	4K / 7.6 GB	5	0
MainPHI3	4K / 7.6 GB	9	0
Model	4K / 7.6 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than njaana/phi3-mini-new-model-with-lora-merged.