flint APEX needs about 26.3 GB of memory at its main file (a 24.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 7 quants, from 14.8 GB to 28.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
Flint APEX – 39.8B Mixture‑of‑Experts model for coding agents
Flint APEX is a 39.8B‑parameter Mixture‑of‑Experts model with 2.5B active parameters per token. It supports up to 262,144 tokens of context and is optimized for coding agent tasks. The model is available in several GGUF quantizations.
Good at
- Coding agent tasks
- Reasoning with tools
- Large context handling
Limits
- Requires llama.cpp with Flint support
- No vision capabilities
- License type is other
Best for
- Developing coding assistants
- Large‑context code analysis
- Tool‑integrated LLM workflows
Who it’s for. Engineers and researchers building coding agents that need large context and expert routing. The model is suitable for developers who can run llama.cpp with Flint support and have sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.8 GB | 16.1 GB | Too big | Get file → | |
| — | 18.4 GB | 19.7 GB | Too big | Get file → | |
| — | 18.4 GB | 19.7 GB | Too big | Get file → | |
| — | 24.9 GB | 26.3 GB | Too big | Get file → | |
| — | 24.9 GB | 26.3 GB | Too big | Get file → | |
| — | 28.5 GB | 29.9 GB | Too big | Get file → | |
| — | 28.5 GB | 29.9 GB | Too big | Get file → |
For 8 GB VRAM, use the 14.79 GB file (16.1 GB memory at 8 k context). For 12 GB VRAM, the 18.42 GB file (19.7 GB memory) is suitable. For larger GPUs, the 24.94 GB or 28.55 GB files provide higher precision with 26.3 GB or 29.9 GB memory respectively. Estimates are approximate.
What GPU do you need for flint APEX?
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: the best quant that fits is the main file (18.4 GB file, about 19.7 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (28.5 GB file, about 29.9 GB in use).
Which flint APEX quant should you choose?
If memory is tight, the smallest file is the first one in the table at 14.8 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 APEX
How much VRAM does flint APEX need?
About 26.3 GB at its main file with an 8K context window. That is the 24.9 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 APEX on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of flint APEX GGUF?
It depends on the quant: file is 14.8 GB, file is 18.4 GB, file is 18.4 GB, file is 24.9 GB, file is 24.9 GB, file is 28.5 GB and 1 more.
What context length does flint APEX 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 APEX GGUF?
The files are on Hugging Face in the mudler/flint-APEX-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 APEX 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 Flint APEX on 8 GB VRAM?
Yes, the 14.79 GB GGUF file uses about 16.1 GB of VRAM at 8 k context, which fits within 8 GB when using GPU memory sharing and swapping.
Does Flint APEX support vision tasks?
No, the model has no vision capabilities.
What llama.cpp commit is required?
Use llama.cpp commit a37cc461 or later, which includes Flint support.