CO

gguf BF16 Comet 60B A12B

CometGGUF by FelladrinUpdated 2026-11-10
Download on Hugging Face
Parameters60.3B
Context1024K
Layers89
Architecturenemotron_h_moe
Smallest quant120.7 GB
Quick answer

gguf BF16 Comet 60B A12B needs about 133.1 GB of memory at BF16 (a 120.7 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 47.8 GB.

gguf BF16 Comet 60B A12B is a 60.3B-parameter Comet model in GGUF format, quantized by Felladrin. Its trained context length is 1024K tokens. The repository has 1 quant file, from 120.7 GB (BF16) to 120.7 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF16120.7 GB 133.1 GB
Too big Get file →

What GPU do you need for gguf BF16 Comet 60B A12B?

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 gguf BF16 Comet 60B A12B quant should you choose?

BF16 (120.7 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

Architecturenemotron_h_moe
Parameters60.3B (approximate, mixture of experts)
Active parameters12B
Layers89
Trained context1,048,576 tokens
KV cache (fp16)1424 KB per token

Source

Quantized byFelladrin
FamilyComet
Downloads (HF)142
Last updated2026-11-10

Frequently asked questions about gguf BF16 Comet 60B A12B

How much VRAM does gguf BF16 Comet 60B A12B need?

About 133.1 GB at BF16 with an 8K context window. That is the 120.7 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 gguf BF16 Comet 60B A12B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 133.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gguf BF16 Comet 60B A12B GGUF?

It depends on the quant: BF16 is 120.7 GB.

What context length does gguf BF16 Comet 60B A12B support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 11.9 GB at 8K and 47.8 GB at 32K.

Where can I download gguf BF16 Comet 60B A12B GGUF?

The files are on Hugging Face in the Felladrin/gguf-BF16-Comet-60B-A12B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gguf BF16 Comet 60B A12B use?

Hugging Face lists the license as openmdw-1.1. 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 Felladrin

All by Felladrin →

More Comet models

All Comet →

Other large models

All large models →