Artemis 31B v1.2 needs about 57.0 GB of memory at Q5_K_M (a 24.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Artemis 31B v1.2 is a 30.7B-parameter Artemis model in GGUF format, quantized by DeusImperator. Its trained context length is 256K tokens. The repository has 1 quant file, from 24.2 GB (Q5_K_M) to 24.2 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 24.2 GB | 57.0 GB | Too big | Get file → |
What GPU do you need for Artemis 31B v1.2?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Artemis 31B v1.2 quant should you choose?
Q5_K_M (24.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Artemis 31B v1.2
How much VRAM does Artemis 31B v1.2 need?
About 57.0 GB at Q5_K_M with an 8K context window. That is the 24.2 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 Artemis 31B v1.2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 57.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Artemis 31B v1.2 GGUF?
It depends on the quant: Q5_K_M is 24.2 GB.
What context length does Artemis 31B v1.2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.
Where can I download Artemis 31B v1.2 GGUF?
The files are on Hugging Face in the DeusImperator/Artemis-31B-v1.2-GGUF-long-ctx repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.