CO

contracts_all_v1_oss20b_HF

ContractsGGUF by berkesencanUpdated 2025-10-23
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant22.3 GB
Quick answer

contracts_all_v1_oss20b_HF needs about 23.2 GB of memory at Q8_0 (a 22.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

contracts_all_v1_oss20b_HF is a 20.9B-parameter Contracts model in GGUF format, quantized by berkesencan. Its trained context length is 128K tokens. The repository has 1 quant file, from 22.3 GB (Q8_0) to 22.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_022.3 GB 23.2 GB
Too big Get file →

What GPU do you need for contracts_all_v1_oss20b_HF?

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: the best quant that fits is Q8_0 (22.3 GB file, about 23.2 GB in use).

Which contracts_all_v1_oss20b_HF quant should you choose?

Q8_0 (22.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters20.9B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized byberkesencan
FamilyContracts
Downloads (HF)6
Last updated2025-10-23

Frequently asked questions about contracts_all_v1_oss20b_HF

How much VRAM does contracts_all_v1_oss20b_HF need?

About 23.2 GB at Q8_0 with an 8K context window. That is the 22.3 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 contracts_all_v1_oss20b_HF on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of contracts_all_v1_oss20b_HF GGUF?

It depends on the quant: Q8_0 is 22.3 GB.

What context length does contracts_all_v1_oss20b_HF support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download contracts_all_v1_oss20b_HF GGUF?

The files are on Hugging Face in the berkesencan/contracts_all_v1_oss20b_HF-Q8_0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of contracts_all_v1_oss20b_HF

Similar models

Browse all →

More from berkesencan

All by berkesencan →

More Contracts models

All Contracts →

Other medium models

All medium models →