Morax 24B v2 needs about 11.7 GB of memory at IQ3_XS (a 9.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 9 quants, from 6.5 GB (IQ2_XXS) to 13.5 GB (IQ4_NL). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Morax 24B v2 is a 23.6B-parameter Morax model in GGUF format, quantized by Naphula. Its trained context length is 128K tokens. The repository has 9 quant files, from 6.5 GB (IQ2_XXS) to 13.5 GB (IQ4_NL).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 6.5 GB | 8.4 GB | Too big | Get file → | |
| IQ2_S | 7.5 GB | 9.3 GB | Too big | Get file → | |
| IQ2_M | 8.1 GB | 10.0 GB | Too big | Get file → | |
| IQ3_XXS | 9.3 GB | 11.1 GB | Too big | Get file → | |
| IQ3_XS | 9.9 GB | 11.7 GB | Too big | Get file → | |
| IQ3_S | 10.4 GB | 12.3 GB | Too big | Get file → | |
| IQ3_M | 10.7 GB | 12.5 GB | Too big | Get file → | |
| IQ4_XS | 12.8 GB | 14.6 GB | Too big | Get file → | |
| IQ4_NL | 13.5 GB | 15.3 GB | Too big | Get file → |
What GPU do you need for Morax 24B v2?
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: the best quant that fits is IQ3_XS (9.9 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_NL (13.5 GB file, about 15.3 GB in use).
Which Morax 24B v2 quant should you choose?
IQ3_XS (9.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ2_XXS at 6.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Morax 24B v2
How much VRAM does Morax 24B v2 need?
About 11.7 GB at IQ3_XS with an 8K context window. That is the 9.9 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 Morax 24B v2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Morax 24B v2 GGUF?
It depends on the quant: IQ2_XXS is 6.5 GB, IQ2_S is 7.5 GB, IQ2_M is 8.1 GB, IQ3_XXS is 9.3 GB, IQ3_XS is 9.9 GB, IQ3_S is 10.4 GB and 3 more.
What context length does Morax 24B v2 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Morax 24B v2 GGUF?
The files are on Hugging Face in the Naphula/Morax-24B-v2-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.