DE

HeatSeeker 284B A13B

DeepSeekGGUF by UltimateIntentUpdated 2026-08-28
Download on Hugging Face
Parameters284B
Context1024K
Layers—
Architecturedeepseek4
Smallest quant64.5 GB
Quick answer

HeatSeeker 284B A13B needs about 192.9 GB of memory at Q4_K_M (a 171.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 64.5 GB (IQ1_M) to 171.8 GB (Q4_K_M).

HeatSeeker 284B A13B – 284 B parameter DeepSeek model

HeatSeeker 284B A13B is a 284 B parameter DeepSeek model based on Huihui‑DeepSeek‑V4‑Flash‑0731‑abliterated. It supports llama.cpp and ds4. The model has a trained context of 1 048 576 tokens and is released under the MIT license.

Good at

  • Large‑context generation
  • High‑parameter capacity
  • DeepSeek architecture

Limits

  • No vision support
  • Risk of sensitive outputs
  • Requires research‑level usage

Best for

  • Research experiments
  • Controlled content generation
  • High‑capacity text modeling

Who it’s for. Researchers and developers needing a large‑parameter DeepSeek model for controlled experiments. The model is not suited for production or public deployment due to limited safety filtering.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M64.5 GB 72.8 GB
Too big Get file →
IQ2_XS88.9 GB 100.1 GB
Too big Get file →
IQ3_M123.9 GB 139.3 GB
Too big Get file →
Q4_K_M171.8 GB 192.9 GB
Too big Get file →

For 8 GB VRAM use IQ1_M (64.53 GB file, ~72.8 GB memory at 8 k context). For 12 GB VRAM use IQ2_XS (88.88 GB file, ~100.1 GB memory). For 16 GB VRAM use IQ3_M (123.9 GB file, ~139.3 GB memory). For 24 GB VRAM use Q4_K_M (171.83 GB file, ~192.9 GB memory). Estimates are approximate.

What GPU do you need for HeatSeeker 284B A13B?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which HeatSeeker 284B A13B quant should you choose?

Q4_K_M is the usual starting point for HeatSeeker 284B A13B: it balances file size and quality well. Here it is a 171.8 GB file.

If memory is tight, the smallest file is IQ1_M at 64.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek4
Parameters284B
Trained context1,048,576 tokens

Source

Quantized byUltimateIntent
FamilyDeepSeek
Licensemit
Downloads (HF)861
Last updated2026-08-28

Frequently asked questions about HeatSeeker 284B A13B

How much VRAM does HeatSeeker 284B A13B need?

About 192.9 GB at Q4_K_M with an 8K context window. That is the 171.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run HeatSeeker 284B A13B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 72.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of HeatSeeker 284B A13B GGUF?

It depends on the quant: IQ1_M is 64.5 GB, IQ2_XS is 88.9 GB, IQ3_M is 123.9 GB, Q4_K_M is 171.8 GB.

What context length does HeatSeeker 284B A13B support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download HeatSeeker 284B A13B GGUF?

The files are on Hugging Face in the UltimateIntent/HeatSeeker-284B-A13B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does HeatSeeker 284B A13B use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run HeatSeeker 284B A13B on 8 GB VRAM?

Use the IQ1_M quantized file; it requires about 72.8 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does this model support image inputs?

No, the model has no vision support.

Is the model safe for public use?

The model has reduced safety filtering and is recommended only for research or controlled environments.

Similar models

Browse all →

More from UltimateIntent

All by UltimateIntent →

More DeepSeek models

All DeepSeek →

Other large models

All large models →