Flint-DFlash2 needs about 0.9 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.2 GB (Q4_K_M) to 0.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.
Flint-DFlash2: a 0.403B parameter speculative drafting model
Flint-DFlash2 is a 0.403 billion parameter model built on the dflash architecture. It supports reasoning and multi‑turn tool use. The model is released under the apache‑2.0 license and is available in several GGUF quantizations.
Good at
- reasoning
- tools
- speculative drafting
Limits
- trained context 262144 tokens
- no vision support
- requires speculative decoding server
Best for
- drafting tokens for larger models
- tool‑based agent workflows
- code‑related reasoning tasks
Who it’s for. Developers building speculative decoding pipelines or agents that need a lightweight drafting model. The model is suitable for environments that can host a speculative decoding server and have access to a GPU for the target model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.0 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 1.0 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.1 GB | Fits | Get file → | |
| BF16 | 0.8 GB | 1.5 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_K_M (0.24 GB, ~0.9 GB memory at 8 k context) is recommended. If 12 GB VRAM is available, Q5_K_M (0.29 GB, ~1 GB) or Q6_K (0.34 GB, ~1 GB) can be used. For larger memory budgets, Q8_0 (0.43 GB, ~1.1 GB) or BF16 (0.81 GB, ~1.5 GB) provide higher precision.
What GPU do you need for Flint-DFlash2?
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 BF16 (0.8 GB file, about 1.5 GB in use).
Which Flint-DFlash2 quant should you choose?
Q4_K_M is the usual starting point for Flint-DFlash2: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.4 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Flint-DFlash2
How much VRAM does Flint-DFlash2 need?
About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.2 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-DFlash2 on an 8 GB GPU?
Yes, with BF16: the 0.8 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Flint-DFlash2 GGUF?
It depends on the quant: Q4_K_M is 0.2 GB, Q5_K_M is 0.3 GB, Q6_K is 0.3 GB, Q8_0 is 0.4 GB, BF16 is 0.8 GB.
What context length does Flint-DFlash2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.7 GB at 32K.
Where can I download Flint-DFlash2 GGUF?
The files are on Hugging Face in the incoai/Flint-DFlash2-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-DFlash2 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-DFlash2 on 8 GB VRAM?
Yes, the Q4_K_M quantization is 0.24 GB and uses about 0.9 GB of VRAM at 8 k context, which fits in 8 GB.
Does Flint-DFlash2 support vision tasks?
No, the model only supports text input and output.