NVFP4 - a kaitchup Collection

kaitchup 's Collections

NVFP4

EoRA Adapters for Qwen2.5 and Qwen3

Quantized Qwen3

2-bit Qwen2.5 72B Instruct

Quantized QwQ 32B

Quantized Phi-4 Mini

Quantized Mistral Small 3

Quantized DeepSeek R1 Distill

Quantized Falcon3

Quantized Llama 3.3

Quantized EuroLLM

Quantized Tulu 3 and OLMo 2

Quantized Qwen2.5

Opus Translation Datasets

GPTQ

Yi

Contaminated Mistral 7B and TinyLlama

Llama 3 70B ExLlamaV2 (bpw: 4.0, 3.5, 3.0, 2.5, and 2.18)

[Basics] Quantized Phi-3

[Basics] AutoRound: Llama 3

Quantized Llama 3.1

The Minitron Models and Their Teachers, Quantized

Minivoc

NVFP4

updated about 11 hours ago

LLMs quantized with LLM Compressor to NVFP4. Check the JSON files in the model directories for more information.