FA

Falcon3 7B Instruct

FalconGGUF by tiiuaeUpdated 2025-03-05
Download on Hugging Face
Parameters7.46B
Context32K
Layers28
Architecturellama
Smallest quant2.9 GB
Quick answer

Falcon3 7B Instruct needs about 6.0 GB of memory at Q4_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 9 quants, from 2.9 GB (Q2_K) to 14.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Falcon3 7B Instruct – 7.46B parameter instruction‑tuned LLM

Falcon3 7B Instruct is a 7.46B parameter transformer model with 28 decoder blocks and 32K context length. It supports English, French, Spanish, and Portuguese. The model is available in multiple GGUF quantizations.

Good at

  • Reasoning and mathematics tasks
  • Instruction following
  • Multilingual support

Limits

  • No vision capabilities
  • Requires at least 4.3 GB VRAM for Q2_K
  • License: TII Falcon-LLM License 2.0

Best for

  • Chatbot prototypes
  • Code generation assistance
  • Academic research on LLM reasoning

Who it’s for. Developers and researchers needing a compact, instruction‑tuned model for natural language tasks. The model is suitable for local deployment with llama.cpp and supports a wide range of languages.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.9 GB 4.3 GB
Fits Get file →
Q3_K_M3.7 GB 5.1 GB
Fits Get file →
Q4_04.3 GB 5.7 GB
Fits Get file →
Q4_K_M4.6 GB 6.0 GB
Fits Get file →
Q5_05.2 GB 6.6 GB
Fits Get file →
Q5_K_M5.3 GB 6.8 GB
Fits Get file →
Q6_K6.1 GB 7.6 GB
Tight Get file →
Q8_07.9 GB 9.4 GB
Too big Get file →
F1614.9 GB 16.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.57 GB, estimated 6 GB memory). If 12 GB VRAM is available, Q5_K_M (5.32 GB, 6.8 GB memory) offers higher quality. For the best accuracy, choose Q8_0 (7.93 GB, 9.4 GB memory).

What GPU do you need for Falcon3 7B Instruct?

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 Q4_K_M (4.6 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.1 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.9 GB file, about 9.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.9 GB file, about 9.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.9 GB file, about 16.4 GB in use).

Which Falcon3 7B Instruct quant should you choose?

Q4_K_M is the usual starting point for Falcon3 7B Instruct: it balances file size and quality well. Here it is a 4.6 GB file.

The Q8_0 file is 7.9 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 Q2_K at 2.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.46B
Layers28
Trained context32,768 tokens
KV cache (fp16)112 KB per token

Source

Quantized bytiiuae
FamilyFalcon
Licenseother
Downloads (HF)1,386
Last updated2025-03-05

Frequently asked questions about Falcon3 7B Instruct

How much VRAM does Falcon3 7B Instruct need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 4.6 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 7B Instruct on an 8 GB GPU?

Yes, with Q6_K: the 6.1 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Falcon3 7B Instruct GGUF?

It depends on the quant: Q2_K is 2.9 GB, Q3_K_M is 3.7 GB, Q4_0 is 4.3 GB, Q4_K_M is 4.6 GB, Q5_0 is 5.2 GB, Q5_K_M is 5.3 GB and 3 more.

What context length does Falcon3 7B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 Falcon3 7B Instruct GGUF?

The files are on Hugging Face in the tiiuae/Falcon3-7B-Instruct-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 7B Instruct 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 7B Instruct on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 6 GB VRAM at 8K context, which fits within an 8 GB GPU.

Does the model support image input?

No, Falcon3 7B Instruct is a text‑only model and does not process vision data.

What languages can the model understand?

The model supports English, French, Spanish, and Portuguese.

Other GGUFs of Falcon3-7B-Instruct

Similar models

Browse all →

More from tiiuae

All by tiiuae →

More Falcon models

All Falcon →

Other small models

All small models →