Flint 40B A2.5B Abliterated needs about 25.5 GB of memory at Q4_K_M (a 24.2 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.5 GB to 32.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
Flint 40B A2.5B Abliterated – a 39.8B parameter Mixture of Experts model
Flint 40B A2.5B Abliterated is a 39.8B parameter model with 2.5B active parameters. It supports reasoning and tool usage. The model is released under the apache-2.0 license.
Good at
- Reasoning
- Tool integration
- Large context support
Limits
- No vision support
- Requires large VRAM for higher quants
- License is apache-2.0
Best for
- Complex reasoning tasks
- Tool‑driven workflows
- Long‑form content generation
Who it’s for. Developers and researchers needing a large, Mixture of Experts model for advanced reasoning and tool use. The model is suitable for applications that can accommodate its memory requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.8 GB | Fits | Get file → | |
| IQ1_S | 8.2 GB | 9.5 GB | Too big | Get file → | |
| IQ1_M | 9.1 GB | 10.4 GB | Too big | Get file → | |
| IQ2_XXS | 10.6 GB | 11.9 GB | Too big | Get file → | |
| IQ2_XS | 11.8 GB | 13.1 GB | Too big | Get file → | |
| IQ2_S | 11.9 GB | 13.2 GB | Too big | Get file → | |
| IQ2_M | 13.1 GB | 14.4 GB | Too big | Get file → | |
| Q2_K_S | 13.6 GB | 14.9 GB | Too big | Get file → | |
| Q2_K | 14.7 GB | 16.0 GB | Too big | Get file → | |
| IQ3_XXS | 15.4 GB | 16.8 GB | Too big | Get file → | |
| IQ3_XS | 16.4 GB | 17.7 GB | Too big | Get file → | |
| Q3_K_S | 17.3 GB | 18.6 GB | Too big | Get file → | |
| IQ3_S | 17.3 GB | 18.6 GB | Too big | Get file → | |
| IQ3_M | 17.5 GB | 18.8 GB | Too big | Get file → | |
| Q3_K_M | 19.1 GB | 20.4 GB | Too big | Get file → | |
| Q3_K_L | 20.7 GB | 22.0 GB | Too big | Get file → | |
| IQ4_XS | 21.3 GB | 22.6 GB | Too big | Get file → | |
| Q4_0 | 22.6 GB | 23.9 GB | Too big | Get file → | |
| Q4_K_S | 22.7 GB | 24.0 GB | Too big | Get file → | |
| Q4_K_M | 24.2 GB | 25.5 GB | Too big | Get file → | |
| Q4_1 | 25.0 GB | 26.3 GB | Too big | Get file → | |
| Q5_K_S | 27.5 GB | 28.8 GB | Too big | Get file → | |
| Q5_K_M | 28.3 GB | 29.6 GB | Too big | Get file → | |
| Q6_K | 32.7 GB | 34.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 8.18 GB, estimated memory 9.5 GB). For 16 GB VRAM, IQ1_M (9.08 GB, 10.4 GB) or IQ2_XXS (10.56 GB, 11.9 GB) are suitable. For 32 GB VRAM, Q4_K_M (24.17 GB, 25.5 GB) or Q5_K_M (28.31 GB, 29.6 GB) provide higher quality.
What GPU do you need for Flint 40B A2.5B Abliterated?
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 IQ2_XXS (10.6 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K (14.7 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_S (22.7 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (28.3 GB file, about 29.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (32.7 GB file, about 34.0 GB in use).
Which Flint 40B A2.5B Abliterated quant should you choose?
Q4_K_M is the usual starting point for Flint 40B A2.5B Abliterated: it balances file size and quality well. Here it is a 24.2 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
Frequently asked questions about Flint 40B A2.5B Abliterated
How much VRAM does Flint 40B A2.5B Abliterated need?
About 25.5 GB at Q4_K_M with an 8K context window. That is the 24.2 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 Flint 40B A2.5B Abliterated 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 40B A2.5B Abliterated GGUF?
It depends on the quant: file is 0.5 GB, IQ1_S is 8.2 GB, IQ1_M is 9.1 GB, IQ2_XXS is 10.6 GB, IQ2_XS is 11.8 GB, IQ2_S is 11.9 GB and 18 more.
What context length does Flint 40B A2.5B Abliterated 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 40B A2.5B Abliterated GGUF?
The files are on Hugging Face in the mradermacher/Flint-40B-A2.5B-abliterated-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 Flint 40B A2.5B Abliterated 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 this model on 8 GB VRAM?
Use the IQ1_S quant which requires about 9.5 GB of VRAM at 8k context. It is the smallest quant that supports the model.
Does this model support vision?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.