psgokulkrishnan/phi-4-mini-instruct-GGUF overview
https://huggingface.co/microsoft/Phi 4 mini instruct Usage: from llama cpp import Llama GGUF PATH = "./phi 4 mini instruct Q4 K M.gguf" print "⏳ Initializing l…
Runs locally from ~2.32 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| phi_4_mini_instruct_Q4_K_M.gguf | GGUF | Q4_K_M | 2.32 GB | Download |
| phi_4_mini_instruct_Q5_K_M.gguf | GGUF | Q5_K_M | 2.62 GB | Download |
| phi_4_mini_instruct_Q6_K.gguf | GGUF | Q6_K | 2.94 GB | Download |
| phi_4_mini_instruct_Q8_0.gguf | GGUF | Q8_0 | 3.80 GB | Download |
| phi_4_mini_instruct_uncompressed.gguf | GGUF | GGUF | 7.15 GB | Download |
Model Details
| Model ID | psgokulkrishnan/phi-4-mini-instruct-GGUF |
|---|---|
| Author | psgokulkrishnan |
| Pipeline | text-generation |
| License | mit |
| Base model | — |
| Last modified | 2026-07-02T08:24:08.000Z |
Model README
---
language:
- multilingual
- ar
- zh
- cs
- da
- nl
- en
- fi
- fr
- de
- he
- hu
- it
- ja
- ko
- 'no'
- pl
- pt
- ru
- es
- sv
- th
- tr
- uk
library_name: transformers
license: mit
license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- code
widget:
- messages:
- role: user
content: Can you provide ways to eat combinations of bananas and dragonfruits?
---
https://huggingface.co/microsoft/Phi-4-mini-instruct
Usage:
from llama_cpp import Llama
GGUF_PATH = "./phi_4_mini_instruct_Q4_K_M.gguf"
print("⏳ Initializing long-context GGUF engine directly into memory layout...")
llm = Llama(
model_path=GGUF_PATH,
n_ctx=16384,
flash_attn=True,
n_threads=4,
verbose=False
)
Run psgokulkrishnan/phi-4-mini-instruct-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models