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.
| LLM Name | DeepSeek Prover V2 671B GGUF |
| Repository 🤗 | https://huggingface.co/unsloth/DeepSeek-Prover-V2-671B-GGUF |
| Base Model(s) | |
| Model Size | 671b |
| Required VRAM | 250 GB |
| Updated | 2026-05-23 |
| Maintainer | unsloth |
| Model Type | deepseek_v3 |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | DeepseekV3ForCausalLM |
| License | mit |
| Context Length | 163840 |
| Model Max Length | 163840 |
| Transformers Version | 4.52.3 |
| Vocabulary Size | 129280 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| RakutenAI 3.0 MLX 4bit | 160K / 198.7 GB | 109 | 2 |
| DeepSeek V3.1 8bit | 160K / 177.8 GB | 2077 | 3 |
| DeepSeek V3.1 Terminus 4bit | 160K / 190.1 GB | 143 | 2 |
| DeepSeek V3.1 Base 4bit | 160K / 190.1 GB | 148 | 3 |
| DeepSeek R1 0528 5bit | 160K / 231 GB | 102 | 3 |
| DeepSeek V3 AWQ | 160K / 351.9 GB | 280 | 35 |
| R1 1776 | 160K / 243.4 GB | 855 | 2324 |
| DeepSeek Prover V2 671B | 160K / 189 GB | 704 | 829 |
| Cogito 671B V2.1 | 160K / 219.9 GB | 175 | 29 |
| Deepseek V3.1 MLX 5.5bit | 160K / 231 GB | 339 | 5 |
🆘 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! 🌟