FA

Falcon3 1B Instruct 1.58bit

FalconGGUF by XXXXyuUpdated 2026-01-01
Download on Hugging Face
Parameters1.67B
Context8K
Layers18
Architecturellama
Smallest quant0.6 GB
Quick answer

Falcon3 1B Instruct 1.58bit needs about 1.8 GB of memory at its main file (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.6 GB to 0.7 GB.

Falcon3 1B Instruct 1.58bit – a compact, 1.58‑bit ternary‑packed LLM

Falcon3 1B Instruct 1.58bit is a 1.67 billion‑parameter causal decoder model. It is trained for instruction following and supports tool usage. The model is available in GGUF format with ternary packing for efficient on‑device inference.

Good at

  • Instruction following
  • Tool usage
  • Low‑bit inference

Limits

  • No vision support
  • License is other
  • No explicit language list

Best for

  • Chat assistants
  • Code generation prompts
  • Lightweight inference on edge

Who it’s for. Developers needing a small, low‑bit model for instruction tasks. Researchers interested in ternary‑packed LLMs and efficient deployment on devices with limited memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.6 GB 1.7 GB
Fits Get file →
—0.6 GB 1.7 GB
Fits Get file →
—0.7 GB 1.8 GB
Fits Get file →
—0.7 GB 1.8 GB
Fits Get file →
—0.7 GB 1.8 GB
Fits Get file →

The available GGUF files are all quantized to an unknown packing. Each file is 0.6 GB or 0.66 GB and requires approximately 1.7 GB or 1.8 GB of VRAM at 8 k context. For 8 GB VRAM, any of the 0.6 GB files will fit comfortably. For 4 GB VRAM, the 0.6 GB files are still suitable but will use most of the memory.

What GPU do you need for Falcon3 1B Instruct 1.58bit?

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 the main file (0.7 GB file, about 1.8 GB in use).

Which Falcon3 1B Instruct 1.58bit quant should you choose?

If memory is tight, the smallest file is the first one in the table at 0.6 GB, with the quality trade-offs that come with fewer bits.

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 byXXXXyu
FamilyFalcon
Licenseother
Downloads (HF)813
Last updated2026-01-01

Frequently asked questions about Falcon3 1B Instruct 1.58bit

How much VRAM does Falcon3 1B Instruct 1.58bit need?

About 1.8 GB at its main file with an 8K context window. That is the 0.7 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 1.58bit on an 8 GB GPU?

Yes, with the smaller files: the 0.7 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Falcon3 1B Instruct 1.58bit GGUF?

It depends on the quant: file is 0.6 GB, file is 0.6 GB, file is 0.7 GB, file is 0.7 GB, file is 0.7 GB.

What context length does Falcon3 1B Instruct 1.58bit 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 1.58bit GGUF?

The files are on Hugging Face in the XXXXyu/Falcon3-1B-Instruct-1.58bit-vlut-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 1.58bit 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.

Can I run Falcon3 1B Instruct 1.58bit on 8 GB VRAM?

Yes, the 0.6 GB GGUF files require about 1.7 GB of VRAM at 8 k context, leaving ample headroom.

Does this model support vision tasks?

No, the model has no vision capabilities.

What quantization is used in the GGUF files?

The files use an unknown ternary packing; the exact quant name is not specified.

Similar models

Browse all →

More from XXXXyu

All by XXXXyu →

More Falcon models

All Falcon →

Other tiny models

All tiny models →