HE

Hermes4.3 36B heretic bf16

HermesGGUF by salamanderDixonUpdated 2026-09-12
Download on Hugging Face
Parameters36.2B
Context512K
Layers64
Architectureseed_oss
Smallest quant72.3 GB
Quick answer

Hermes4.3 36B heretic bf16 needs about 75.0 GB of memory at BF16 (a 72.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Hermes4.3 36B heretic bf16 is a 36.2B-parameter Hermes model in GGUF format, quantized by salamanderDixon. Its trained context length is 512K tokens. The repository has 1 quant file, from 72.3 GB (BF16) to 72.3 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1672.3 GB 75.0 GB
Too big Get file →

What GPU do you need for Hermes4.3 36B heretic bf16?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 Hermes4.3 36B heretic bf16 quant should you choose?

BF16 (72.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureseed_oss
Parameters36.2B
Layers64
Trained context524,288 tokens
KV cache (fp16)256 KB per token

Source

Quantized bysalamanderDixon
FamilyHermes
Licenseapache-2.0
Downloads (HF)32
Last updated2026-09-12

Frequently asked questions about Hermes4.3 36B heretic bf16

How much VRAM does Hermes4.3 36B heretic bf16 need?

About 75.0 GB at BF16 with an 8K context window. That is the 72.3 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 Hermes4.3 36B heretic bf16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 75.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Hermes4.3 36B heretic bf16 GGUF?

It depends on the quant: BF16 is 72.3 GB.

What context length does Hermes4.3 36B heretic bf16 support?

The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Hermes4.3 36B heretic bf16 GGUF?

The files are on Hugging Face in the salamanderDixon/Hermes4.3-36B-heretic-bf16.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 Hermes4.3 36B heretic bf16 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from salamanderDixon

All by salamanderDixon →

More Hermes models

All Hermes →

Other large models

All large models →