MO

model5 sft

ModelGGUF by jerrycheng233Updated 2026-03-28
Download on Hugging Face
Parameters29.9B
Context198K
Layers—
Architecturedeepseek2
Smallest quant10.0 GB
Quick answer

model5 sft needs about 11.7 GB of memory at BF16 (a 10.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 10.0 GB (BF16) to 31.8 GB (Q8_0).

model5 sft is a 29.9B-parameter Model model in GGUF format, quantized by jerrycheng233. Its trained context length is 198K tokens. The repository has 2 quant files, from 10.0 GB (BF16) to 31.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1610.0 GB 11.7 GB
Too big Get file →
Q8_031.8 GB 36.2 GB
Too big Get file →

What GPU do you need for model5 sft?

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: the best quant that fits is BF16 (10.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (10.0 GB file, about 11.7 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (10.0 GB file, about 11.7 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (10.0 GB file, about 11.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (31.8 GB file, about 36.2 GB in use).

Which model5 sft quant should you choose?

BF16 (10.0 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

Architecturedeepseek2
Parameters29.9B
Trained context202,752 tokens

Source

Quantized byjerrycheng233
FamilyModel
Downloads (HF)25
Last updated2026-03-28

Frequently asked questions about model5 sft

How much VRAM does model5 sft need?

About 11.7 GB at BF16 with an 8K context window. That is the 10.0 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 model5 sft on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of model5 sft GGUF?

It depends on the quant: BF16 is 10.0 GB, Q8_0 is 31.8 GB.

What context length does model5 sft support?

The GGUF header lists a trained context length of 202,752 tokens (198K).

Where can I download model5 sft GGUF?

The files are on Hugging Face in the jerrycheng233/model5_sft_gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from jerrycheng233

All by jerrycheng233 →

More Model models

All Model →

Other medium models

All medium models →