FA

Falcon

FalconGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters8.11B
Context2K
Layers43
Architecturefalcon
Smallest quant1.9 GB
Quick answer

Falcon needs about 7.0 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 1.9 GB (IQ1_S) to 6.7 GB (Q6_K).

Falcon 10B multilingual GGUF model

Falcon 10B is a multilingual language model merged from Falcon2-8B and Falcon2-5.5B. It offers 8,110 million parameters and a 2,048 token context window. The model is available in multiple quantizations for varied memory budgets.

Good at

  • Multilingual text generation
  • Fast inference on low‑end GPUs
  • Large context handling

Limits

  • No vision support
  • License not specified
  • Requires 8‑k context for memory estimates

Best for

  • Chatbots needing multilingual support
  • Rapid prototyping on limited VRAM
  • Research on language model behavior

Who it’s for. Developers and researchers who need a multilingual LLM that can run on consumer hardware. The model is suitable for those who can manage the memory requirements and are comfortable with GGUF format.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.9 GB 2.8 GB
Fits Get file →
IQ1_M2.1 GB 3.0 GB
Fits Get file →
IQ2_XXS2.4 GB 3.2 GB
Fits Get file →
IQ2_XS2.6 GB 3.4 GB
Fits Get file →
IQ2_S2.7 GB 3.6 GB
Fits Get file →
IQ2_M2.9 GB 3.8 GB
Fits Get file →
Q2_K3.2 GB 4.0 GB
Fits Get file →
IQ3_XXS3.3 GB 4.2 GB
Fits Get file →
IQ3_XS3.6 GB 4.4 GB
Fits Get file →
IQ3_S3.7 GB 4.5 GB
Fits Get file →
Q3_K_S3.7 GB 4.5 GB
Fits Get file →
IQ3_M3.8 GB 4.7 GB
Fits Get file →
Q3_K_M4.0 GB 4.9 GB
Fits Get file →
Q3_K_L4.3 GB 5.1 GB
Fits Get file →
IQ4_XS4.5 GB 5.3 GB
Fits Get file →
Q4_K_S4.7 GB 5.6 GB
Fits Get file →
Q4_04.7 GB 5.6 GB
Fits Get file →
Q4_K_M5.0 GB 5.9 GB
Fits Get file →
Q5_K_S5.7 GB 6.5 GB
Fits Get file →
Q5_K_M6.0 GB 6.9 GB
Fits Get file →
Q6_K6.7 GB 7.6 GB
Tight Get file →

For 8‑GB VRAM, use Q4_K_S (file size 4.7 GB, memory 6.6 GB). If 12‑GB VRAM is available, Q5_K_M (file size 6.01 GB, memory 8 GB) provides higher quality. For 16‑GB VRAM, Q6_K (file size 6.72 GB, memory 8.7 GB) offers the best fidelity.

What GPU do you need for Falcon?

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 IQ1_M (2.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.0 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.0 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.7 GB in use).

Which Falcon quant should you choose?

Q4_K_M is the usual starting point for Falcon: it balances file size and quality well. Here it is a 5.0 GB file.

If memory is tight, the smallest file is IQ1_S at 1.9 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

Architecturefalcon
Parameters8.11B
Layers43
Trained context2,048 tokens
KV cache (fp16)172 KB per token

Source

Quantized bymradermacher
FamilyFalcon
Downloads (HF)1,717
Last updated2024-12-16

Frequently asked questions about Falcon

How much VRAM does Falcon need?

About 7.0 GB at Q4_K_M with an 8K context window. That is the 5.0 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 on an 8 GB GPU?

Yes, with Q5_K_M: the 6.0 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Falcon GGUF?

It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.1 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.7 GB, IQ2_M is 2.9 GB and 15 more.

What context length does Falcon support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.4 GB at 8K and 0.4 GB at 2K.

Where can I download Falcon GGUF?

The files are on Hugging Face in the mradermacher/Falcon2-10B-multilingual-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Falcon 10B on 8 GB VRAM?

Yes, using the Q4_K_S quantization which requires approximately 6.6 GB of VRAM at 8k context.

Does Falcon 10B support vision tasks?

No, the model does not include vision capabilities.

What is the context length of Falcon 10B?

The model supports a 2,048 token context window.

Other GGUFs of Falcon2-8B-multilingual

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Falcon models

All Falcon →

Other small models

All small models →