Arsenic Shahrazad 12B v4.4.3 mtp needs about 3.0 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 1.1 GB (Q4_K_M) to 8.7 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 5.5 GB.
Arsenic Shahrazad 12B v4.4.3 mtp is a 12.2B-parameter Arsenic model in GGUF format, quantized by Lambent. Its trained context length is 1000K tokens. The repository has 7 quant files, from 1.1 GB (Q4_K_M) to 8.7 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.1 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 3.7 GB | Fits | Get file → | |
| IQ3_M | 5.7 GB | 7.6 GB | Tight | Get file → | |
| IQ4_XS | 6.7 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_M | 7.5 GB | 9.4 GB | Too big | Get file → | |
| Q5_K_M | 8.7 GB | 10.6 GB | Too big | Get file → |
What GPU do you need for Arsenic Shahrazad 12B v4.4.3 mtp?
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 Q8_0 (1.8 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (1.8 GB file, about 3.7 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_M (5.7 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (8.7 GB file, about 10.6 GB in use).
Which Arsenic Shahrazad 12B v4.4.3 mtp quant should you choose?
Q4_K_M is the usual starting point for Arsenic Shahrazad 12B v4.4.3 mtp: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.8 GB, about 1.6 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 Arsenic Shahrazad 12B v4.4.3 mtp
How much VRAM does Arsenic Shahrazad 12B v4.4.3 mtp need?
About 3.0 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Arsenic Shahrazad 12B v4.4.3 mtp on an 8 GB GPU?
Yes, with IQ3_M: the 5.7 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Arsenic Shahrazad 12B v4.4.3 mtp GGUF?
It depends on the quant: Q4_K_M is 1.1 GB, Q6_K is 1.4 GB, Q8_0 is 1.8 GB, IQ3_M is 5.7 GB, IQ4_XS is 6.7 GB, Q4_K_M is 7.5 GB and 1 more.
What context length does Arsenic Shahrazad 12B v4.4.3 mtp support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.5 GB at 32K.
Where can I download Arsenic Shahrazad 12B v4.4.3 mtp GGUF?
The files are on Hugging Face in the Lambent/Arsenic-Shahrazad-12B-v4.4.3-mtp-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Arsenic Shahrazad 12B v4.4.3 mtp use?
Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.