FL

Flint

FlintGGUF by AtomicChatUpdated 2026-10-28
Download on Hugging Face
Parameters39.8B
Context256K
Layers49
Architectureflint
Smallest quant13.3 GB
Quick answer

Flint needs about 20.4 GB of memory at IQ3_S (a 19.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 13.3 GB (IQ2_XXS) to 42.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.

39.8B mixture‑of‑experts coding model

Flint is a 39.8 billion‑parameter mixture‑of‑experts model designed for coding tasks. It supports text input and output, reasoning, and multi‑turn tool use. The model is released under the apache‑2.0 license.

Good at

  • coding
  • reasoning
  • tool use

Limits

  • no vision support
  • requires large VRAM for full context
  • trained context tokens 262144

Best for

  • debugging code
  • implementing features
  • writing tests

Who it’s for. Developers and researchers needing a large coding model with active‑parameter support. The model is suitable for local deployment on GPUs with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS13.3 GB 14.6 GB
Too big Get file →
IQ2_M16.4 GB 17.7 GB
Too big Get file →
IQ3_S19.1 GB 20.4 GB
Too big Get file →
IQ4_XS24.5 GB 25.8 GB
Too big Get file →
Q6_K34.7 GB 36.1 GB
Too big Get file →
Q8_042.9 GB 44.2 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (13.28 GB file, 14.6 GB memory at 8k context). For 16 GB VRAM, IQ2_M (16.36 GB file, 17.7 GB memory). For 32 GB VRAM, Q6_K (34.74 GB file, 36.1 GB memory).

What GPU do you need for Flint?

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: the best quant that fits is IQ2_XXS (13.3 GB file, about 14.6 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_S (19.1 GB file, about 20.4 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ4_XS (24.5 GB file, about 25.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (42.9 GB file, about 44.2 GB in use).

Which Flint quant should you choose?

IQ3_S (19.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ2_XXS at 13.3 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

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

Source

Quantized byAtomicChat
FamilyFlint
Licenseapache-2.0
Downloads (HF)6,927
Last updated2026-10-28

Frequently asked questions about Flint

How much VRAM does Flint need?

About 20.4 GB at IQ3_S with an 8K context window. That is the 19.1 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Flint GGUF?

It depends on the quant: IQ2_XXS is 13.3 GB, IQ2_M is 16.4 GB, IQ3_S is 19.1 GB, IQ4_XS is 24.5 GB, Q6_K is 34.7 GB, Q8_0 is 42.9 GB.

What context length does Flint 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 GGUF?

The files are on Hugging Face in the AtomicChat/Flint-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 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 on 8 GB VRAM?

Yes, the IQ2_XXS quantization file is 13.28 GB and requires about 14.6 GB memory at 8k context, which fits an 8 GB VRAM setup with swapping.

Does Flint support vision?

No, Flint only supports text input and output.

Other GGUFs of flint

Similar models

Browse all →

More from AtomicChat

All by AtomicChat →

More Flint models

All Flint →

Other large models

All large models →