FA

Falcon3 Mamba 7B Instruct

FalconGGUF by mradermacherUpdated 2024-12-18
Download on Hugging Face
Parameters7.27B
Context1024K
Layers64
Architecturemamba
Smallest quant1.6 GB
Quick answer

Falcon3 Mamba 7B Instruct needs about 5.2 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 22 quants, from 1.6 GB (IQ1_S) to 6.0 GB (Q6_K).

Falcon3 Mamba 7B Instruct – 7.27B parameter instruction model

Falcon3 Mamba 7B Instruct is a 7.27B parameter instruction-following model based on the Mamba architecture. It supports a context length of 32K tokens and was trained on English data with additional STEM, code, and conversation fine‑tuning.

Good at

  • Instruction following
  • Code generation
  • Mathematics tasks

Limits

  • No vision support
  • License is TII Falcon-LLM License 2.0
  • Requires large VRAM for higher quant levels

Best for

  • Chatbots needing long context
  • Code assistance
  • Academic research

Who it’s for. Developers and researchers who need a large instruction‑tuned model with extended context. The model is suitable for applications that require detailed reasoning and code generation in English.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 2.3 GB
Fits Get file →
IQ1_M1.8 GB 2.5 GB
Fits Get file →
IQ2_XXS2.1 GB 2.8 GB
Fits Get file →
IQ2_XS2.3 GB 3.0 GB
Fits Get file →
IQ2_S2.3 GB 3.1 GB
Fits Get file →
IQ2_M2.5 GB 3.3 GB
Fits Get file →
Q2_K2.6 GB 3.4 GB
Fits Get file →
Q2_K_S2.6 GB 3.4 GB
Fits Get file →
IQ3_XXS2.9 GB 3.8 GB
Fits Get file →
IQ3_M3.3 GB 4.2 GB
Fits Get file →
IQ3_S3.3 GB 4.2 GB
Fits Get file →
IQ3_XS3.3 GB 4.2 GB
Fits Get file →
Q3_K_L3.3 GB 4.2 GB
Fits Get file →
Q3_K_M3.3 GB 4.2 GB
Fits Get file →
Q3_K_S3.3 GB 4.2 GB
Fits Get file →
IQ4_XS4.0 GB 5.0 GB
Fits Get file →
Q4_04.2 GB 5.2 GB
Fits Get file →
Q4_K_M4.2 GB 5.2 GB
Fits Get file →
Q4_K_S4.2 GB 5.2 GB
Fits Get file →
Q5_K_M5.1 GB 6.2 GB
Fits Get file →
Q5_K_S5.1 GB 6.2 GB
Fits Get file →
Q6_K6.0 GB 7.2 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.2 GB, estimated 5.2 GB memory). For 12 GB VRAM, Q5_K_M (5.08 GB, 6.2 GB memory) is suitable. For 16 GB VRAM, Q6_K (6.01 GB, 7.2 GB memory) can be used. Estimates are approximate.

What GPU do you need for Falcon3 Mamba 7B Instruct?

These figures add the file size, an fp16 KV cache at an 8K context window 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 IQ3_XXS (2.9 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_0 (4.2 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 7.2 GB in use).

Which Falcon3 Mamba 7B Instruct quant should you choose?

Q4_K_M is the usual starting point for Falcon3 Mamba 7B Instruct: it balances file size and quality well. Here it is a 4.2 GB file.

If memory is tight, the smallest file is IQ1_S at 1.6 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

Architecturemamba
Parameters7.27B
Layers64
Trained context1,048,576 tokens

Source

Quantized bymradermacher
FamilyFalcon
Licenseother
Downloads (HF)419
Last updated2024-12-18

Frequently asked questions about Falcon3 Mamba 7B Instruct

How much VRAM does Falcon3 Mamba 7B Instruct need?

About 5.2 GB at Q4_K_M with an 8K context window. That is the 4.2 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 Mamba 7B Instruct on an 8 GB GPU?

Yes, with Q6_K: the 6.0 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.1 GB, IQ2_XS is 2.3 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 16 more.

What context length does Falcon3 Mamba 7B Instruct support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download Falcon3 Mamba 7B Instruct GGUF?

The files are on Hugging Face in the mradermacher/Falcon3-Mamba-7B-Instruct-i1-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 Mamba 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 Mamba 7B Instruct on 8 GB VRAM?

Yes, using the Q4_K_M quant file which requires about 5.2 GB of VRAM at 8K context.

Does this model support vision tasks?

No, the model does not have vision capabilities.

What is the maximum context length I can use?

The model supports up to 32K tokens of context.

Other GGUFs of Falcon3-Mamba-7B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Falcon models

All Falcon →

Other small models

All small models →