DeepSeek Prover V2 671B GGUF by unsloth

 »  All LLMs  »  unsloth  »  DeepSeek Prover V2 671B GGUF   URL Share it on

DeepSeek Prover V2 671B GGUF is an open-source language model by unsloth. Features: 671b LLM, VRAM: 250GB, Context: 160K, License: mit, Quantized, LLM Explorer Score: 0.21.

Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Conversational   Custom code   Deepseek   Deepseek v3   En   Endpoints compatible   Fp8   Gguf   Quantized   Region:us   Unsloth

DeepSeek Prover V2 671B GGUF Benchmarks

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

DeepSeek Prover V2 671B GGUF Parameters and Internals

LLM NameDeepSeek Prover V2 671B GGUF
Repository 🤗https://huggingface.co/unsloth/DeepSeek-Prover-V2-671B-GGUF 
Base Model(s)  DeepSeek Prover V2 671B   deepseek-ai/DeepSeek-Prover-V2-671B
Model Size671b
Required VRAM250 GB
Updated2026-05-23
Maintainerunsloth
Model Typedeepseek_v3
Model Files  404.0 GB   250.0 GB   295.0 GB   384.0 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureDeepseekV3ForCausalLM
Licensemit
Context Length163840
Model Max Length163840
Transformers Version4.52.3
Vocabulary Size129280
Torch Data Typebfloat16

Best Alternatives to DeepSeek Prover V2 671B GGUF

Best Alternatives
Context / RAM
Downloads
Likes
RakutenAI 3.0 MLX 4bit160K / 198.7 GB1092
DeepSeek V3.1 8bit160K / 177.8 GB20773
DeepSeek V3.1 Terminus 4bit160K / 190.1 GB1432
DeepSeek V3.1 Base 4bit160K / 190.1 GB1483
DeepSeek R1 0528 5bit160K / 231 GB1023
DeepSeek V3 AWQ160K / 351.9 GB28035
R1 1776160K / 243.4 GB8552324
DeepSeek Prover V2 671B160K / 189 GB704829
Cogito 671B V2.1160K / 219.9 GB17529
Deepseek V3.1 MLX 5.5bit160K / 231 GB3395
Note: green Score (e.g. "73.2") means that the model is better than unsloth/DeepSeek-Prover-V2-671B-GGUF.

Rank the DeepSeek Prover V2 671B GGUF Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 53999 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a