SIP jmed llm 3 8x13b AC 32k instruct needs about 51.3 GB of memory at Q4_K_M (a 45.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 40.3 GB (IQ4_XS) to 146.3 GB (BF16).
SIP jmed llm 3 8x13b AC 32k instruct is a 73.2B-parameter Sip model in GGUF format, quantized by hiratagoh. Its trained context length is 32K tokens. The repository has 6 quant files, from 40.3 GB (IQ4_XS) to 146.3 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 40.3 GB | 45.6 GB | Too big | Get file → | |
| Q4_K_M | 45.4 GB | 51.3 GB | Too big | Get file → | |
| Q5_K_M | 52.7 GB | 59.5 GB | Too big | Get file → | |
| Q6_K | 60.5 GB | 68.3 GB | Too big | Get file → | |
| Q8_0 | 77.7 GB | 87.6 GB | Too big | Get file → | |
| BF16 | 146.3 GB | 164.4 GB | Too big | Get file → |
What GPU do you need for SIP jmed llm 3 8x13b AC 32k instruct?
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: 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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is IQ4_XS (40.3 GB file, about 45.6 GB in use).
Which SIP jmed llm 3 8x13b AC 32k instruct quant should you choose?
Q4_K_M is the usual starting point for SIP jmed llm 3 8x13b AC 32k instruct: it balances file size and quality well. Here it is a 45.4 GB file.
The Q8_0 file is 77.7 GB, about 1.7 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.
If memory is tight, the smallest file is IQ4_XS at 40.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about SIP jmed llm 3 8x13b AC 32k instruct
How much VRAM does SIP jmed llm 3 8x13b AC 32k instruct need?
About 51.3 GB at Q4_K_M with an 8K context window. That is the 45.4 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 SIP jmed llm 3 8x13b AC 32k instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 45.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SIP jmed llm 3 8x13b AC 32k instruct GGUF?
It depends on the quant: IQ4_XS is 40.3 GB, Q4_K_M is 45.4 GB, Q5_K_M is 52.7 GB, Q6_K is 60.5 GB, Q8_0 is 77.7 GB, BF16 is 146.3 GB.
What context length does SIP jmed llm 3 8x13b AC 32k instruct support?
The GGUF header lists a trained context length of 32,768 tokens (32K).
Where can I download SIP jmed llm 3 8x13b AC 32k instruct GGUF?
The files are on Hugging Face in the hiratagoh/SIP-jmed-llm-3-8x13b-AC-32k-instruct-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 SIP jmed llm 3 8x13b AC 32k instruct 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.