knaif needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 1.4 GB (Q6_K) to 2.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
knaif – fine‑tuned Qwen3‑1.7B for generating validated action plans
knaif is a fine‑tuned Qwen3‑1.7B model that produces strict JSON action plans for command‑line tools. It is trained on ffmpeg and documents skills and only proposes the plan, never executes code.
Good at
- Generating validated JSON action plans
- Fine‑tuned for ffmpeg and documents skills
- Supports deterministic plan validation
Limits
- No vision support
- Requires 32,768 context length
- License is apache‑2.0
Best for
- Command‑line tool integration
- Automated media processing
- Document manipulation
Who it’s for. Developers building local command‑line assistants that need reliable action plans. Users of knaif.org and knaif.dev can integrate the model into their workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 1.4 GB | 3.1 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q6_K (1.42 GB file, ~3.1 GB VRAM at 8 k context). For 12 GB VRAM, Q4_K_M (2.5 GB file, ~4.2 GB VRAM at 8 k context) is suitable. Memory estimates are approximate.
What GPU do you need for knaif?
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 Q6_K (1.4 GB file, about 3.1 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (2.5 GB file, about 4.2 GB in use).
Which knaif quant should you choose?
Q4_K_M is the usual starting point for knaif: it balances file size and quality well. Here it is a 2.5 GB file.
If memory is tight, the smallest file is Q6_K at 1.4 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about knaif
How much VRAM does knaif need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 knaif on an 8 GB GPU?
Yes, with Q4_K_M: the 2.5 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of knaif GGUF?
It depends on the quant: Q6_K is 1.4 GB, Q6_K is 1.4 GB, Q4_K_M is 2.5 GB, Q4_K_M is 2.5 GB.
What context length does knaif support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download knaif GGUF?
The files are on Hugging Face in the blackdeep/knaif repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does knaif 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 knaif on 8 GB VRAM?
Yes, the Q6_K quantization uses about 3.1 GB VRAM at 8 k context, fitting within an 8 GB GPU.
Does knaif support vision tasks?
No, the model has no vision capabilities.