FL

Flint NVFP4 Preview

FlintGGUF by RecursiveSIUpdated 2026-10-21
Download on Hugging Face
Parameters39.8B
Context256K
Layers49
Architectureflint
Smallest quant22.9 GB
Quick answer

Flint NVFP4 Preview needs about 24.2 GB of memory at its main file (a 22.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.

Flint NVFP4 Preview – 39.8B parameter model for NVIDIA GPUs

Flint NVFP4 Preview is a 39.8 billion‑parameter model optimized for NVIDIA GPUs using llama.cpp with CUDA. The 22.86 GB GGUF file contains weights, tokenizer, and chat template. It supports a 262,144‑token context and requires at least 48 GB of GPU memory.

Good at

  • Large context handling
  • CUDA‑optimized inference
  • Flint architecture support

Limits

  • Requires 48 GB GPU memory
  • No vision support
  • License is Apache‑2.0

Best for

  • Long‑form text generation
  • Complex reasoning tasks
  • Chat applications with extended context

Who it’s for. Developers and researchers needing high‑capacity language models on NVIDIA hardware. Suitable for applications that can allocate large GPU memory and use llama.cpp with CUDA.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—22.9 GB 24.2 GB
Too big Get file →

The only available quant is unknown, with a 22.86 GB file. Memory usage is approximately 24.2 GB at 8 k context. For 8 k context, the model will need around 24 GB of VRAM. No other quants are provided.

What GPU do you need for Flint NVFP4 Preview?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is the main file (22.9 GB file, about 24.2 GB in use).

Specifications

Architecture from the GGUF header

Architectureflint
Parameters39.8B (approximate, mixture of experts)
Layers49
Trained context262,144 tokens
KV cache (fp16)98 KB per token

Source

Quantized byRecursiveSI
FamilyFlint
Licenseapache-2.0
Downloads (HF)26,722
Last updated2026-10-21

Frequently asked questions about Flint NVFP4 Preview

How much VRAM does Flint NVFP4 Preview need?

About 24.2 GB at its main file with an 8K context window. That is the 22.9 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 Flint NVFP4 Preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Flint NVFP4 Preview GGUF?

It depends on the quant: file is 22.9 GB.

What context length does Flint NVFP4 Preview support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.3 GB at 32K.

Where can I download Flint NVFP4 Preview GGUF?

The files are on Hugging Face in the RecursiveSI/flint-nvfp4-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 Flint NVFP4 Preview use?

Hugging Face lists the license as apache-2.0. 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 Flint NVFP4 on 8 GB VRAM?

No. The model requires at least 48 GB of GPU memory for full operation.

What context length does Flint NVFP4 support?

It supports a 262,144‑token context length.

Is there a license restriction?

The model is released under Apache License 2.0, which allows free use and modification.

Similar models

Browse all →

More from RecursiveSI

All by RecursiveSI →

More Flint models

All Flint →

Other large models

All large models →