FA

Falcon E 1.2 10B Exp

FalconGGUF by axolotl-ai-coUpdated 2026-04-30
Download on Hugging Face
Parameters10.3B
Context64K
Layers40
Architecturellama
Smallest quant3.0 GB
Quick answer

Falcon E 1.2 10B Exp needs about 4.9 GB of memory at TQ2_0 (a 3.0 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 5.4 GB.

Falcon E 1.2 10B Exp is a 10.3B-parameter Falcon model in GGUF format, quantized by axolotl-ai-co. Its trained context length is 64K tokens. The repository has 1 quant file, from 3.0 GB (TQ2_0) to 3.0 GB (TQ2_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ2_03.0 GB 4.9 GB
Fits Get file →

What GPU do you need for Falcon E 1.2 10B Exp?

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 TQ2_0 (3.0 GB file, about 4.9 GB in use).

Which Falcon E 1.2 10B Exp quant should you choose?

TQ2_0 (3.0 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.3B
Layers40
Trained context65,536 tokens
KV cache (fp16)160 KB per token

Source

Quantized byaxolotl-ai-co
FamilyFalcon
Licenseapache-2.0
Downloads (HF)38
Last updated2026-04-30

Frequently asked questions about Falcon E 1.2 10B Exp

How much VRAM does Falcon E 1.2 10B Exp need?

About 4.9 GB at TQ2_0 with an 8K context window. That is the 3.0 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 Falcon E 1.2 10B Exp on an 8 GB GPU?

Yes, with TQ2_0: the 3.0 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 Falcon E 1.2 10B Exp GGUF?

It depends on the quant: TQ2_0 is 3.0 GB.

What context length does Falcon E 1.2 10B Exp support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Falcon E 1.2 10B Exp GGUF?

The files are on Hugging Face in the axolotl-ai-co/Falcon-E-1.2-10B-Exp-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 Falcon E 1.2 10B Exp 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 axolotl-ai-co

All by axolotl-ai-co →

More Falcon models

All Falcon →

Other medium models

All medium models →