LLM EXPLORER 61,918 MODELS INDEXED

DeepSeek V4 Flash GGUF by unsloth

By unsloth · 30807 downloads
HF Repo ↗ Copy URL

DeepSeek V4 Flash GGUF is an open-source language model by unsloth. Features: LLM, Context: 1024K, License: mit, Quantized, LLM Explorer Score: 0.53, ELO: 1436.

  Arxiv:2606.19348 Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Conversational   Deepseek   Deepseek v4   Endpoints compatible   Fp8   Gguf   Imatrix   Quantized   Region:us   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/DeepSeek-V4-Flash-GGUF 

DeepSeek V4 Flash GGUF Benchmarks

LMSys ELO 1436 vs 1272 (so35) 12.9%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

DeepSeek V4 Flash GGUF Parameters and Internals

LLM NameDeepSeek V4 Flash GGUF
Repository 🤗https://huggingface.co/unsloth/DeepSeek-V4-Flash-GGUF 
Base Model(s)  DeepSeek V4 Flash   deepseek-ai/DeepSeek-V4-Flash
Updated2026-09-13
Maintainerunsloth
Model Typedeepseek_v4
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureDeepseekV4ForCausalLM
Licensemit
Context Length1048576
Model Max Length1048576
Transformers Version4.57.1
Vocabulary Size129280
Torch Data Typebfloat16