flint needs about 26.3 GB of memory at Q4_K_M (a 25.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 0.5 GB to 29.0 GB (Q5_K_M). 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 language model designed for coding tasks. It supports reasoning, multi‑turn tool use, and text input/output. The model is released under the apache‑2.0 license.
Good at
- reasoning
- tools
- coding
Limits
- requires large VRAM for full context
- no vision support
- licensed under apache‑2.0
Best for
- debugging code
- implementing features
- writing tests
Who it’s for. Flint is aimed at developers and coding agents that need advanced reasoning and tool‑use capabilities in a large‑parameter model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.8 GB | Fits | Get file → | |
| IQ4_XS | 22.2 GB | 23.6 GB | Too big | Get file → | |
| Q4_K_M | 25.0 GB | 26.3 GB | Too big | Get file → | |
| Q5_K_M | 29.0 GB | 30.3 GB | Too big | Get file → |
For 24 GB GPUs, IQ4_XS (22.24 GB file, 23.6 GB memory at 8 k context) is recommended. For 32 GB+ VRAM or GPU+RAM split, Q4_K_M (25.02 GB file, 26.3 GB memory) or Q5_K_M (28.98 GB file, 30.3 GB memory) are suitable. Estimates are approximate.
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: the best quant that fits is the main file (0.5 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.8 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.8 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.8 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (22.2 GB file, about 23.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (29.0 GB file, about 30.3 GB in use).
Which flint quant should you choose?
Q4_K_M is the usual starting point for flint: it balances file size and quality well. Here it is a 25.0 GB file.
If memory is tight, the smallest file is the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about flint
How much VRAM does flint need?
About 26.3 GB at Q4_K_M with an 8K context window. That is the 25.0 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 flint on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of flint GGUF?
It depends on the quant: file is 0.5 GB, IQ4_XS is 22.2 GB, Q4_K_M is 25.0 GB, Q5_K_M is 29.0 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 terelabs/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 a 24 GB GPU?
Yes, the IQ4_XS quantization (22.24 GB file) fits a 24 GB GPU with a small context or partial offload.
Does Flint support vision tasks?
No, Flint only supports text input and output.