ComfyUI Starter Packs needs about 11.3 GB of memory at Q4_K_M (a 9.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 3.4 GB (Q5_K_M) to 9.8 GB (Q6_K).
ComfyUI Starter Packs is a 4.76B-parameter Comfyui model in GGUF format, quantized by zhangxiaole258. Its trained context length is 512 tokens. The repository has 24 quant files, from 3.4 GB (Q5_K_M) to 9.8 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 3.4 GB | 3.9 GB | Fits | Get file → | |
| Q5_K_M | 4.1 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_S | 5.2 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_S | 5.2 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_S | 5.2 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_S | 5.2 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 5.4 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 6.8 GB | 7.3 GB | Tight | Get file → | |
| Q4_0 | 6.8 GB | 7.3 GB | Tight | Get file → | |
| Q3_K_M | 7.2 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_M | 7.2 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_M | 7.2 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_M | 7.2 GB | 7.7 GB | Tight | Get file → | |
| Q5_K_S | 8.3 GB | 8.8 GB | Too big | Get file → | |
| Q5_0 | 8.3 GB | 8.8 GB | Too big | Get file → | |
| Q5_0 | 8.3 GB | 8.8 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 8.8 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 8.9 GB | Too big | Get file → | |
| Q5_K_M | 8.4 GB | 9.0 GB | Too big | Get file → | |
| Q4_K_M | 9.7 GB | 10.2 GB | Too big | Get file → | |
| Q4_K_M | 9.7 GB | 10.2 GB | Too big | Get file → | |
| Q4_K_M | 9.7 GB | 10.2 GB | Too big | Get file → | |
| Q4_K_M | 9.7 GB | 10.2 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 10.4 GB | Too big | Get file → |
What GPU do you need for ComfyUI Starter Packs?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q5_K_M (4.1 GB file, about 5.1 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_M (5.4 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 11.5 GB in use).
Which ComfyUI Starter Packs quant should you choose?
Q4_K_M is the usual starting point for ComfyUI Starter Packs: it balances file size and quality well. Here it is a 9.7 GB file.
If memory is tight, the smallest file is Q5_K_M at 3.4 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ComfyUI Starter Packs
How much VRAM does ComfyUI Starter Packs need?
About 11.3 GB at Q4_K_M with an 8K context window. That is the 9.7 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 ComfyUI Starter Packs on an 8 GB GPU?
Yes, with Q3_K_M: the 5.4 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ComfyUI Starter Packs GGUF?
It depends on the quant: Q5_K_M is 3.4 GB, Q5_K_M is 4.1 GB, Q3_K_S is 5.2 GB, Q3_K_S is 5.2 GB, Q3_K_S is 5.2 GB, Q3_K_S is 5.2 GB and 18 more.
What context length does ComfyUI Starter Packs support?
The GGUF header lists a trained context length of 512 tokens (512).
Where can I download ComfyUI Starter Packs GGUF?
The files are on Hugging Face in the zhangxiaole258/ComfyUI-Starter-Packs repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does ComfyUI Starter Packs 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.