FA

Falcon3 10B Instruct

FalconGGUF by duyntnetUpdated 2024-12-29
Download on Hugging Face
Parameters10.3B
Context32K
Layers40
Architecturellama
Smallest quant2.4 GB
Quick answer

Falcon3 10B Instruct needs about 8.1 GB of memory at Q4_K_M (a 6.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 27 quants, from 2.4 GB (IQ1_S) to 11.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Falcon3 10B Instruct is a 10.3B-parameter Falcon model in GGUF format, quantized by duyntnet. Its trained context length is 32K tokens. The repository has 27 quant files, from 2.4 GB (IQ1_S) to 11.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 4.2 GB
Fits Get file →
IQ1_M2.6 GB 4.4 GB
Fits Get file →
IQ2_XXS2.9 GB 4.7 GB
Fits Get file →
IQ2_XS3.2 GB 5.0 GB
Fits Get file →
IQ2_S3.3 GB 5.2 GB
Fits Get file →
IQ2_M3.6 GB 5.4 GB
Fits Get file →
Q2_K_S3.7 GB 5.5 GB
Fits Get file →
Q2_K3.9 GB 5.8 GB
Fits Get file →
IQ3_XXS4.1 GB 5.9 GB
Fits Get file →
IQ3_XS4.4 GB 6.2 GB
Fits Get file →
IQ3_S4.6 GB 6.4 GB
Fits Get file →
Q3_K_S4.6 GB 6.4 GB
Fits Get file →
IQ3_M4.7 GB 6.5 GB
Fits Get file →
Q3_K_M5.1 GB 6.9 GB
Fits Get file →
Q3_K_L5.5 GB 7.3 GB
Tight Get file →
IQ4_XS5.6 GB 7.4 GB
Tight Get file →
IQ4_NL5.9 GB 7.7 GB
Tight Get file →
Q4_05.9 GB 7.8 GB
Tight Get file →
Q4_K_S6.0 GB 7.8 GB
Tight Get file →
Q4_K_M6.3 GB 8.1 GB
Too big Get file →
Q4_16.5 GB 8.4 GB
Too big Get file →
Q5_K_S7.1 GB 9.0 GB
Too big Get file →
Q5_07.2 GB 9.0 GB
Too big Get file →
Q5_K_M7.3 GB 9.2 GB
Too big Get file →
Q5_17.8 GB 9.6 GB
Too big Get file →
Q6_K8.5 GB 10.3 GB
Too big Get file →
Q8_011.0 GB 12.8 GB
Too big Get file →

What GPU do you need for Falcon3 10B 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 IQ3_XXS (4.1 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_S (6.0 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.5 GB file, about 10.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.0 GB file, about 12.8 GB in use).

Which Falcon3 10B Instruct quant should you choose?

Q4_K_M is the usual starting point for Falcon3 10B Instruct: it balances file size and quality well. Here it is a 6.3 GB file.

The Q8_0 file is 11.0 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 IQ1_S at 2.4 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
Parameters10.3B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byduyntnet
FamilyFalcon
Licenseother
Downloads (HF)106
Last updated2024-12-29

Frequently asked questions about Falcon3 10B Instruct

How much VRAM does Falcon3 10B Instruct need?

About 8.1 GB at Q4_K_M with an 8K context window. That is the 6.3 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 10B Instruct on an 8 GB GPU?

Yes, with Q4_K_S: the 6.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Falcon3 10B Instruct GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ1_M is 2.6 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.2 GB, IQ2_S is 3.3 GB, IQ2_M is 3.6 GB and 21 more.

What context length does Falcon3 10B 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 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Falcon3 10B Instruct GGUF?

The files are on Hugging Face in the duyntnet/Falcon3-10B-Instruct-imatrix-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 10B 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.

Similar models

Browse all →

More from duyntnet

All by duyntnet →

More Falcon models

All Falcon →

Other medium models

All medium models →