FA

Falcon H1 1.5B Deep Instruct

FalconGGUF by tiiuaeUpdated 2025-07-31
Download on Hugging Face
Parameters1.55B
Context128K
Layers66
Architecturefalcon-h1
Smallest quant0.4 GB
Quick answer

Falcon H1 1.5B Deep Instruct needs about 2.0 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 34 quants, from 0.4 GB (IQ1_M) to 6.2 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 2.2 GB.

Falcon H1 1.5B Deep Instruct – 1.55B parameter causal decoder

Falcon H1 1.5B Deep Instruct is a causal decoder‑only model with 1.55B parameters. It supports English and multilingual text generation. The model is available in multiple GGUF quantizations for llama.cpp.

Good at

  • Reasoning tasks
  • Long context handling
  • Instruction following

Limits

  • No vision support
  • License is Falcon‑LLM
  • Requires 8k context for memory estimates

Best for

  • Chatbots with limited GPU
  • Research prototyping
  • Fine‑tuning small models

Who it’s for. Researchers and developers needing a lightweight, instruction‑tuned Falcon model. The model is suitable for environments with modest GPU memory and for users who prefer GGUF files for llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M0.4 GB 1.5 GB
Fits Get file →
TQ1_00.4 GB 1.5 GB
Fits Get file →
IQ2_XXS0.5 GB 1.5 GB
Fits Get file →
TQ2_00.5 GB 1.5 GB
Fits Get file →
IQ2_XS0.5 GB 1.5 GB
Fits Get file →
IQ2_S0.5 GB 1.6 GB
Fits Get file →
IQ2_M0.6 GB 1.6 GB
Fits Get file →
Q2_K_S0.6 GB 1.6 GB
Fits Get file →
Q2_K0.6 GB 1.6 GB
Fits Get file →
IQ3_XXS0.6 GB 1.7 GB
Fits Get file →
IQ3_XS0.7 GB 1.7 GB
Fits Get file →
IQ3_S0.7 GB 1.8 GB
Fits Get file →
Q3_K_S0.7 GB 1.8 GB
Fits Get file →
IQ3_M0.7 GB 1.8 GB
Fits Get file →
Q3_K0.8 GB 1.8 GB
Fits Get file →
Q3_K_M0.8 GB 1.8 GB
Fits Get file →
Q3_K_L0.8 GB 1.8 GB
Fits Get file →
IQ4_XS0.9 GB 1.9 GB
Fits Get file →
Q4_00.9 GB 2.0 GB
Fits Get file →
IQ4_NL0.9 GB 2.0 GB
Fits Get file →
Q4_K_S0.9 GB 2.0 GB
Fits Get file →
Q4_K0.9 GB 2.0 GB
Fits Get file →
Q4_K_M0.9 GB 2.0 GB
Fits Get file →
Q4_11.0 GB 2.0 GB
Fits Get file →
Q5_01.1 GB 2.1 GB
Fits Get file →
Q5_K_S1.1 GB 2.1 GB
Fits Get file →
Q5_K1.1 GB 2.2 GB
Fits Get file →
Q5_K_M1.1 GB 2.2 GB
Fits Get file →
Q5_11.2 GB 2.2 GB
Fits Get file →
Q6_K1.3 GB 2.3 GB
Fits Get file →
Q8_01.7 GB 2.7 GB
Fits Get file →
BF163.1 GB 4.2 GB
Fits Get file →
F163.1 GB 4.2 GB
Fits Get file →
F326.2 GB 7.3 GB
Tight Get file →

For 8 GB VRAM, use Q4_0 or Q4_K (file size 0.9 GB, memory 2 GB). For 12 GB VRAM, Q5_0 or Q5_K (file size 1.09 GB, memory 2.1 GB). For 16 GB VRAM, Q6_K (file size 1.28 GB, memory 2.3 GB).

What GPU do you need for Falcon H1 1.5B Deep 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: the best quant that fits is Q8_0 (1.7 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (3.1 GB file, about 4.2 GB in use).
  • 8 GB VRAM: the best quant that fits is F32 (6.2 GB file, about 7.3 GB in use).

Which Falcon H1 1.5B Deep Instruct quant should you choose?

Q4_K_M is the usual starting point for Falcon H1 1.5B Deep Instruct: it balances file size and quality well. Here it is a 0.9 GB file.

The Q8_0 file is 1.7 GB, about 1.8 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_M at 0.4 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

Architecturefalcon-h1
Parameters1.55B
Layers66
Trained context131,072 tokens
KV cache (fp16)66 KB per token

Source

Quantized bytiiuae
FamilyFalcon
Licenseother
Downloads (HF)1,344
Last updated2025-07-31

Frequently asked questions about Falcon H1 1.5B Deep Instruct

How much VRAM does Falcon H1 1.5B Deep Instruct need?

About 2.0 GB at Q4_K_M with an 8K context window. That is the 0.9 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 H1 1.5B Deep Instruct on an 8 GB GPU?

Yes, with F32: the 6.2 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Falcon H1 1.5B Deep Instruct GGUF?

It depends on the quant: IQ1_M is 0.4 GB, TQ1_0 is 0.4 GB, IQ2_XXS is 0.5 GB, TQ2_0 is 0.5 GB, IQ2_XS is 0.5 GB, IQ2_S is 0.5 GB and 28 more.

What context length does Falcon H1 1.5B Deep Instruct support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.2 GB at 32K.

Where can I download Falcon H1 1.5B Deep Instruct GGUF?

The files are on Hugging Face in the tiiuae/Falcon-H1-1.5B-Deep-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 Falcon H1 1.5B Deep 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 Falcon H1 1.5B on 8 GB VRAM?

Yes, using Q4_0 or Q4_K quantizations which require about 2 GB of VRAM at 8k context.

Does the model support vision tasks?

No, the model is a text‑only causal decoder.

What license applies to this model?

The model is released under the Falcon‑LLM License.

Other GGUFs of Falcon-H1-1.5B-Deep-Instruct

Similar models

Browse all →

More from tiiuae

All by tiiuae →

More Falcon models

All Falcon →

Other tiny models

All tiny models →