LLM EXPLORER 58,873 MODELS INDEXED

DeepSeek V4 Flash 0731 Abliterated MXFP4 INT8 by Jon-Nielsen

By Jon-Nielsen · 117 downloads
HF Repo ↗ Copy URL

DeepSeek V4 Flash 0731 Abliterated MXFP4 INT8 is an open-source language model by Jon-Nielsen. Features: 159.2b LLM, VRAM: 155.9GB, Context: 1024K, License: mit, LLM Explorer Score: 0.3.

  8-bit   Abliterated   Ampere   Appmana Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Consumer-gpu   Deepseek-v4   Deepseek-v4-flash   Deepseek v4   Dsv4 mxfp4 int8   Endpoints compatible   Flash-mla   Int8   Int8-kv   Long-context   Mixture-of-experts   Mla   Moe   Multi-latent-attention   Mxfp4   Quantization   Region:us   Rtx-3090   Safetensors   Sharded   Sm86   Sm 86   Tensorflow   Uncensored   Vllm   Vllm-fork
Model Card on HF 🤗: https://huggingface.co/Jon-Nielsen/DeepSeek-V4-Flash-0731-Abliterated-MXFP4-INT8 

DeepSeek V4 Flash 0731 Abliterated MXFP4 INT8 Parameters and Internals

LLM NameDeepSeek V4 Flash 0731 Abliterated MXFP4 INT8
Repository 🤗https://huggingface.co/Jon-Nielsen/DeepSeek-V4-Flash-0731-Abliterated-MXFP4-INT8 
Base Model(s)  DeepSeek V4 Flash 0731   lovesenko/DeepSeek-V4-Flash-0731-Abliterated   deepseek-ai/DeepSeek-V4-Flash-0731   lovesenko/DeepSeek-V4-Flash-0731-Abliterated
Model Size159.2b
Required VRAM155.9 GB
Updated2026-08-18
MaintainerJon-Nielsen
Model Typedeepseek_v4
Model Files  1.1 GB: 1-of-48   3.6 GB: 2-of-48   3.6 GB: 3-of-48   3.6 GB: 4-of-48   3.6 GB: 5-of-48   3.6 GB: 6-of-48   3.6 GB: 7-of-48   3.6 GB: 8-of-48   3.6 GB: 9-of-48   3.6 GB: 10-of-48   3.6 GB: 11-of-48   3.6 GB: 12-of-48   3.6 GB: 13-of-48   3.6 GB: 14-of-48   3.6 GB: 15-of-48   3.6 GB: 16-of-48   3.6 GB: 17-of-48   3.6 GB: 18-of-48   3.6 GB: 19-of-48   3.6 GB: 20-of-48   3.6 GB: 21-of-48   3.6 GB: 22-of-48   3.6 GB: 23-of-48   3.6 GB: 24-of-48   3.6 GB: 25-of-48   3.6 GB: 26-of-48   3.6 GB: 27-of-48   3.6 GB: 28-of-48   3.6 GB: 29-of-48   3.6 GB: 30-of-48   3.6 GB: 31-of-48   3.6 GB: 32-of-48   3.6 GB: 33-of-48   3.6 GB: 34-of-48   3.6 GB: 35-of-48   3.6 GB: 36-of-48   3.6 GB: 37-of-48   3.6 GB: 38-of-48   3.6 GB: 39-of-48   3.6 GB: 40-of-48   3.6 GB: 41-of-48   3.6 GB: 42-of-48   3.6 GB: 43-of-48   3.6 GB: 44-of-48
Model ArchitectureDeepseekV4ForCausalLM
Licensemit
Context Length1048576
Model Max Length1048576
Transformers Version4.57.1
Vocabulary Size129280
Torch Data Typebfloat16

Best Alternatives to DeepSeek V4 Flash 0731 Abliterated MXFP4 INT8

Best Alternatives
Context / RAM
Downloads
Likes
...pSeek V4 Flash 0731 MXFP4 INT81024K / 155.9 GB1101