What are the hardware requirements for DeepSeek V4 Flash 0731 Reap 150B?

DeepSeek V4 Flash 0731 Reap 150B requires approximately 4.6 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DeepSeek V4 Flash 0731 Reap 150B and how large is it?

DeepSeek V4 Flash 0731 Reap 150B is developed by puwaer, a model with 150b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate DeepSeek V4 Flash 0731 Reap 150B?

DeepSeek V4 Flash 0731 Reap 150B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DeepSeek V4 Flash 0731 Reap 150B by puwaer — VRAM 4.6GB, 1024K context

Name: DeepSeek V4 Flash 0731 Reap 150B
Author: puwaer

DeepSeek V4 Flash 0731 Reap 150B is an open-source language model by puwaer. Features: 150b LLM, VRAM: 4.6GB, Context: 1024K, License: mit, LLM Explorer Score: 0.29.

Arxiv:2510.13999 Arxiv:2604.04356 8-bit Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Compressed Conversational Deepseek v4 Endpoints compatible Expert-pruning Fp8 Moe Reap Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/puwaer/DeepSeek-V4-Flash-0731-reap-150b

DeepSeek V4 Flash 0731 Reap 150B Parameters and Internals

LLM Name	DeepSeek V4 Flash 0731 Reap 150B
Repository 🤗	https://huggingface.co/puwaer/DeepSeek-V4-Flash-0731-reap-150b
Base Model(s)	DeepSeek V4 Flash 0731 deepseek-ai/DeepSeek-V4-Flash-0731
Model Size	150b
Required VRAM	4.6 GB
Updated	2026-08-11
Maintainer	puwaer
Model Type	deepseek_v4
Model Files	5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 5.0 GB 4.6 GB
Model Architecture	DeepseekV4ForCausalLM
License	mit
Context Length	1048576
Model Max Length	1048576
Transformers Version	4.57.1
Tokenizer Class	PreTrainedTokenizerFast
Beginning of Sentence Token	<｜begin▁of▁sentence｜>
End of Sentence Token	<｜end▁of▁sentence｜>
Vocabulary Size	129280
Torch Data Type	bfloat16

Rank the DeepSeek V4 Flash 0731 Reap 150B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to DeepSeek V4 Flash 0731 Reap 150B

Best Alternatives	Context / RAM	Downloads	Likes
...epSeek V4 Flash 0731 Ream 150B	1024K / 4.6 GB	90	0

Note: green Score (e.g. "73.2") means that the model is better than puwaer/DeepSeek-V4-Flash-0731-reap-150b.