Codette-Ultimate-V4 needs about 20.3 GB of memory at Q4_K_M (a 19.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 16.1 GB to 82.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
32‑billion‑parameter GPT‑OSS‑based model for advanced reasoning
Codette‑Ultimate‑V4 is a 32‑billion‑parameter GPT‑OSS model built on the gpt‑oss‑20b architecture. It supports large context windows of 131072 tokens and is designed for reasoning tasks. The model is released under the MIT license.
Good at
- Large‑context reasoning
- Chain‑of‑thought generation
- Agentic function calling
Limits
- Requires high VRAM (≈20 GB at 8 k context for Q4_K_M quant
- No vision support
- No explicit language support listed
Best for
- Complex reasoning workflows
- Debugging and chain‑of‑thought analysis
- Function‑calling agents
Who it’s for. Developers needing a powerful reasoning engine for local deployment. The model is suitable for research, fine‑tuning, and commercial applications that can accommodate its memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 16.1 GB | 17.0 GB | Too big | Get file → | |
| — | 16.1 GB | 17.0 GB | Too big | Get file → | |
| — | 16.1 GB | 17.0 GB | Too big | Get file → | |
| Q4_K_M | 19.4 GB | 20.3 GB | Too big | Get file → | |
| — | 82.4 GB | 83.3 GB | Too big | Get file → |
For 8 k context, the Q4_K_M quant file (19.44 GB) requires about 20.3 GB of VRAM. The unknown‑quant files are larger (16.1 GB and 82.39 GB) and will need more memory. Choose the Q4_K_M quant if your GPU has at least 20 GB VRAM; otherwise consider the 16.1 GB unknown quant if your GPU has 17 GB VRAM, noting that memory estimates are approximate.
What GPU do you need for Codette-Ultimate-V4?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (19.4 GB file, about 20.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (19.4 GB file, about 20.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_M (19.4 GB file, about 20.3 GB in use).
Which Codette-Ultimate-V4 quant should you choose?
Q4_K_M is the usual starting point for Codette-Ultimate-V4: it balances file size and quality well. Here it is a 19.4 GB file.
If memory is tight, the smallest file is the first one in the table at 16.1 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
Source
Frequently asked questions about Codette-Ultimate-V4
How much VRAM does Codette-Ultimate-V4 need?
About 20.3 GB at Q4_K_M with an 8K context window. That is the 19.4 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 Codette-Ultimate-V4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Codette-Ultimate-V4 GGUF?
It depends on the quant: file is 16.1 GB, file is 16.1 GB, file is 16.1 GB, Q4_K_M is 19.4 GB, file is 82.4 GB.
What context length does Codette-Ultimate-V4 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download Codette-Ultimate-V4 GGUF?
The files are on Hugging Face in the Raiff1982/Codette-Ultimate repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Codette-Ultimate-V4 use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Does the model support vision tasks?
No. The model has no vision capabilities.
What license applies to this model?
The model is released under the MIT license, allowing free use and modification.