calm3 22b RP v2 needs about 23.8 GB of memory at Q4_K_M (a 13.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 7.3 GB (IQ2_S) to 45.1 GB (F16).
calm3 22b RP v2 is a 22.5B-parameter Calm model in GGUF format, quantized by Aratako. Its trained context length is 16K tokens. The repository has 10 quant files, from 7.3 GB (IQ2_S) to 45.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_S | 7.3 GB | 17.5 GB | Too big | Get file → | |
| IQ3_XXS | 8.6 GB | 18.8 GB | Too big | Get file → | |
| IQ3_S | 9.8 GB | 20.0 GB | Too big | Get file → | |
| IQ4_XS | 12.1 GB | 22.3 GB | Too big | Get file → | |
| IQ4_NL | 12.8 GB | 23.0 GB | Too big | Get file → | |
| Q4_K_M | 13.6 GB | 23.8 GB | Too big | Get file → | |
| Q5_K_M | 16.0 GB | 26.2 GB | Too big | Get file → | |
| Q6_K | 18.5 GB | 28.7 GB | Too big | Get file → | |
| Q8_0 | 24.0 GB | 34.1 GB | Too big | Get file → | |
| F16 | 45.1 GB | 55.3 GB | Too big | Get file → |
What GPU do you need for calm3 22b RP 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: 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 (13.6 GB file, about 23.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (18.5 GB file, about 28.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (24.0 GB file, about 34.1 GB in use).
Which calm3 22b RP v2 quant should you choose?
Q4_K_M is the usual starting point for calm3 22b RP v2: it balances file size and quality well. Here it is a 13.6 GB file.
The Q8_0 file is 24.0 GB, about 1.8 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 IQ2_S at 7.3 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 calm3 22b RP v2
How much VRAM does calm3 22b RP v2 need?
About 23.8 GB at Q4_K_M with an 8K context window. That is the 13.6 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 calm3 22b RP v2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of calm3 22b RP v2 GGUF?
It depends on the quant: IQ2_S is 7.3 GB, IQ3_XXS is 8.6 GB, IQ3_S is 9.8 GB, IQ4_XS is 12.1 GB, IQ4_NL is 12.8 GB, Q4_K_M is 13.6 GB and 4 more.
What context length does calm3 22b RP v2 support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 9.7 GB at 8K and 19.3 GB at 16K.
Where can I download calm3 22b RP v2 GGUF?
The files are on Hugging Face in the Aratako/calm3-22b-RP-v2-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 calm3 22b RP v2 use?
Hugging Face lists the license as cc-by-nc-sa-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.