FA

Falcon3 1B Instruct Heretic

FalconGGUF by ChiKoi7Updated 2025-12-09
Download on Hugging Face
Parameters1.67B
Context8K
Layers18
Architecturellama
Smallest quant0.8 GB
Quick answer

Falcon3 1B Instruct Heretic needs about 2.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.8 GB (IQ3_XS) to 3.3 GB (F16).

Falcon3 1B Instruct Heretic is a 1.67B-parameter Falcon model in GGUF format, quantized by ChiKoi7. Its trained context length is 8K tokens. The repository has 14 quant files, from 0.8 GB (IQ3_XS) to 3.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XS0.8 GB 1.9 GB
Fits Get file →
Q3_K_S0.8 GB 1.9 GB
Fits Get file →
IQ3_M0.8 GB 2.0 GB
Fits Get file →
Q3_K_M0.9 GB 2.0 GB
Fits Get file →
Q3_K_L0.9 GB 2.0 GB
Fits Get file →
IQ4_XS1.0 GB 2.1 GB
Fits Get file →
IQ4_NL1.0 GB 2.1 GB
Fits Get file →
Q4_K_S1.0 GB 2.1 GB
Fits Get file →
Q4_K_M1.1 GB 2.2 GB
Fits Get file →
Q5_K_S1.2 GB 2.3 GB
Fits Get file →
Q5_K_M1.2 GB 2.3 GB
Fits Get file →
Q6_K1.4 GB 2.5 GB
Fits Get file →
Q8_01.8 GB 2.9 GB
Fits Get file →
F163.3 GB 4.4 GB
Fits Get file →

What GPU do you need for Falcon3 1B Instruct Heretic?

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: the best quant that fits is Q8_0 (1.8 GB file, about 2.9 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.3 GB file, about 4.4 GB in use).

Which Falcon3 1B Instruct Heretic quant should you choose?

Q4_K_M is the usual starting point for Falcon3 1B Instruct Heretic: it balances file size and quality well. Here it is a 1.1 GB file.

The Q8_0 file is 1.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ3_XS at 0.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.67B
Layers18
Trained context8,192 tokens
KV cache (fp16)72 KB per token

Source

Quantized byChiKoi7
FamilyFalcon
Licenseother
Downloads (HF)132
Last updated2025-12-09

Frequently asked questions about Falcon3 1B Instruct Heretic

How much VRAM does Falcon3 1B Instruct Heretic need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Falcon3 1B Instruct Heretic on an 8 GB GPU?

Yes, with F16: the 3.3 GB file needs about 4.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Falcon3 1B Instruct Heretic GGUF?

It depends on the quant: IQ3_XS is 0.8 GB, Q3_K_S is 0.8 GB, IQ3_M is 0.8 GB, Q3_K_M is 0.9 GB, Q3_K_L is 0.9 GB, IQ4_XS is 1.0 GB and 8 more.

What context length does Falcon3 1B Instruct Heretic support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.6 GB at 8K and 0.6 GB at 8K.

Where can I download Falcon3 1B Instruct Heretic GGUF?

The files are on Hugging Face in the ChiKoi7/Falcon3-1B-Instruct-Heretic-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 Falcon3 1B Instruct Heretic use?

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

Other GGUFs of Falcon3-1B-Instruct

Similar models

Browse all →

More from ChiKoi7

All by ChiKoi7 →

More Falcon models

All Falcon →

Other tiny models

All tiny models →