decision models stable fork needs about 1.6 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.3 GB (Q4_K_M) to 25.1 GB (Q4_K_XL).
Decision Models Stable Fork – a 9.08B DeBERTa‑v3 LLM
Decision Models Stable Fork is a 9.08B parameter DeBERTa‑v3 model. It supports reasoning, tools, and vision. The model is trained on 512 context tokens.
Good at
- reasoning
- tools
- vision
Limits
- 512 context tokens
- no license info
- no vision support details
Best for
- reasoning tasks
- tool integration
- vision prompts
Who it’s for. Developers building applications that require reasoning, tool use, and vision capabilities. The model is suitable for research and production use where these abilities are needed.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_M | 1.7 GB | 2.2 GB | Fits | Get file → | |
| Q4_K_M | 3.1 GB | 3.6 GB | Fits | Get file → | |
| Q4_K_M | 6.5 GB | 7.0 GB | Fits | Get file → | |
| Q8_0 | 9.7 GB | 10.2 GB | Too big | Get file → | |
| Q4_K_XL | 25.1 GB | 25.6 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (0.3 GB, 1.6 GB memory). For 16 GB VRAM use Q4_K_M (1.67 GB, 3 GB memory) or Q8_0 (0.41 GB, 1.7 GB memory). For 32 GB VRAM use Q4_K_XL (25.05 GB, 26.4 GB memory).
What GPU do you need for decision models stable fork?
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 Q4_K_M (1.7 GB file, about 3.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (3.1 GB file, about 4.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (6.5 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.7 GB file, about 11.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.7 GB file, about 11.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (9.7 GB file, about 11.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_XL (25.1 GB file, about 26.4 GB in use).
Which decision models stable fork quant should you choose?
Q4_K_M is the usual starting point for decision models stable fork: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.4 GB, about 1.4 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 decision models stable fork
How much VRAM does decision models stable fork need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.3 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 decision models stable fork on an 8 GB GPU?
Yes, with Q4_K_M: the 6.5 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of decision models stable fork GGUF?
It depends on the quant: Q4_K_M is 0.3 GB, Q8_0 is 0.4 GB, Q4_K_M is 1.7 GB, Q4_K_M is 3.1 GB, Q4_K_M is 6.5 GB, Q8_0 is 9.7 GB and 1 more.
What context length does decision models stable fork support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 512.
Where can I download decision models stable fork GGUF?
The files are on Hugging Face in the runanywhere/decision-models-stable-fork repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, using the Q4_K_M quant (0.3 GB file, 1.6 GB memory at 8k context).
Does the model support vision tasks?
Yes, vision is listed among its detected abilities.
What is the context length of this model?
The model is trained on 512 context tokens.