What are the hardware requirements for Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed?

Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed requires approximately 2.9 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.

Where can I download or evaluate Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed?

Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed by PrunaAI — VRAM 2.9GB, 128K context

Name: Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed
Author: PrunaAI

Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed is an open-source language model by PrunaAI. Features: LLM, VRAM: 2.9GB, Context: 128K, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

4bit Custom code Hqq Instruct Phi3 Pruna-ai Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/PrunaAI/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed

Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed Parameters and Internals

Additional Notes

Results mentioning 'first' are obtained after the first run of the model... 'Sync' metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. 'Async' metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU.

Input Output

Performance Tips:

Test the efficiency gains directly in your use-cases.

LLM Name	Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed
Repository 🤗	https://huggingface.co/PrunaAI/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed
Base Model(s)	ORIGINAL_REPO_NAME /ORIGINAL_REPO_NAME
Required VRAM	2.9 GB
Updated	2025-09-23
Maintainer	PrunaAI
Model Type	phi3
Instruction-Based	Yes
Model Files	2.9 GB
Quantization Type	4bit
Model Architecture	Phi3ForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.48.2
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
Torch Data Type	bfloat16

Rank the Microsoft Phi 3 Mini 128K Instruct HQQ 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 Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed

Best Alternatives	Context / RAM	Downloads	Likes
...m 128K Instruct 8.0bpw H8 EXL2	128K / 13.4 GB	7	4
...m 128K Instruct 6.0bpw H6 EXL2	128K / 10.7 GB	7	3
...dium 128K Instruct 8 0bpw EXL2	128K / 13.4 GB	4	1
...m 128K Instruct 3.0bpw H6 EXL2	128K / 5.6 GB	5	0
...m 128K Instruct 5.0bpw H6 EXL2	128K / 8.9 GB	5	0
...28K Instruct Ov Fp16 Int4 Asym	128K / 2.5 GB	9	0
...128K Instruct HQQ 2bit Smashed	128K / 1.4 GB	8	0
NuExtract Bpw6 EXL2	4K / 3 GB	4	1
...Mini 4K Geminified 3 0bpw EXL2	4K / 1.6 GB	6	0
...uct Abliterated V3 2 2bpw EXL2	4K / 4.2 GB	9	0

Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed.