HU

hunch-1.7b-preview

HunchGGUF by antareslabsUpdated 2026-09-25
Download on Hugging Face
Parameters1.72B
Context40K
Layers28
Architectureqwen3
Smallest quant3.4 GB
Quick answer

hunch-1.7b-preview needs about 4.9 GB of memory at F16 (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

hunch-1.7b-preview is a 1.72B-parameter Hunch model in GGUF format, quantized by antareslabs. Its trained context length is 40K tokens. The repository has 1 quant file, from 3.4 GB (F16) to 3.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F163.4 GB 4.9 GB
Fits Get file →

What GPU do you need for hunch-1.7b-preview?

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: the best quant that fits is F16 (3.4 GB file, about 4.9 GB in use).

Which hunch-1.7b-preview quant should you choose?

F16 (3.4 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

Architectureqwen3
Parameters1.72B
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized byantareslabs
FamilyHunch
Licenseapache-2.0
Downloads (HF)17
Last updated2026-09-25

Frequently asked questions about hunch-1.7b-preview

How much VRAM does hunch-1.7b-preview need?

About 4.9 GB at F16 with an 8K context window. That is the 3.4 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 hunch-1.7b-preview on an 8 GB GPU?

Yes, with F16: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of hunch-1.7b-preview GGUF?

It depends on the quant: F16 is 3.4 GB.

What context length does hunch-1.7b-preview support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download hunch-1.7b-preview GGUF?

The files are on Hugging Face in the antareslabs/hunch-1.7b-preview-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 hunch-1.7b-preview 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 antareslabs

All by antareslabs →

More Hunch models

All Hunch →

Other tiny models

All tiny models →