Aurora Gem Opt lora8 mistral 22b model 15k grb needs about 15.7 GB of memory at Q4_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 20 quants, from 8.3 GB (Q2_K) to 16.7 GB (Q5_1). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.
Aurora Gem Opt lora8 mistral 22b model 15k grb is a 22.2B-parameter Mistral model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 20 quant files, from 8.3 GB (Q2_K) to 16.7 GB (Q5_1).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 8.3 GB | 10.7 GB | Too big | Get file → | |
| IQ3_XS | 9.2 GB | 11.6 GB | Too big | Get file → | |
| Q3_K_S | 9.6 GB | 12.0 GB | Too big | Get file → | |
| IQ3_S | 9.7 GB | 12.1 GB | Too big | Get file → | |
| IQ3_M | 10.1 GB | 12.4 GB | Too big | Get file → | |
| Q3_K | 10.8 GB | 13.1 GB | Too big | Get file → | |
| Q3_K_M | 10.8 GB | 13.1 GB | Too big | Get file → | |
| Q3_K_L | 11.7 GB | 14.1 GB | Too big | Get file → | |
| IQ4_XS | 12.0 GB | 14.4 GB | Too big | Get file → | |
| Q4_0 | 12.6 GB | 14.9 GB | Too big | Get file → | |
| Q4_K_S | 12.7 GB | 15.0 GB | Too big | Get file → | |
| IQ4_NL | 12.7 GB | 15.1 GB | Too big | Get file → | |
| Q4_K | 13.3 GB | 15.7 GB | Too big | Get file → | |
| Q4_K_M | 13.3 GB | 15.7 GB | Too big | Get file → | |
| Q4_1 | 13.9 GB | 16.3 GB | Too big | Get file → | |
| Q5_0 | 15.3 GB | 17.7 GB | Too big | Get file → | |
| Q5_K_S | 15.3 GB | 17.7 GB | Too big | Get file → | |
| Q5_K | 15.7 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_M | 15.7 GB | 18.1 GB | Too big | Get file → | |
| Q5_1 | 16.7 GB | 19.1 GB | Too big | Get file → |
What GPU do you need for Aurora Gem Opt lora8 mistral 22b model 15k grb?
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 Q3_K_S (9.6 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K (13.3 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_1 (16.7 GB file, about 19.1 GB in use).
Which Aurora Gem Opt lora8 mistral 22b model 15k grb quant should you choose?
Q4_K_M is the usual starting point for Aurora Gem Opt lora8 mistral 22b model 15k grb: it balances file size and quality well. Here it is a 13.3 GB file.
If memory is tight, the smallest file is Q2_K at 8.3 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
Frequently asked questions about Aurora Gem Opt lora8 mistral 22b model 15k grb
How much VRAM does Aurora Gem Opt lora8 mistral 22b model 15k grb need?
About 15.7 GB at Q4_K_M with an 8K context window. That is the 13.3 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 Aurora Gem Opt lora8 mistral 22b model 15k grb on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Aurora Gem Opt lora8 mistral 22b model 15k grb GGUF?
It depends on the quant: Q2_K is 8.3 GB, IQ3_XS is 9.2 GB, Q3_K_S is 9.6 GB, IQ3_S is 9.7 GB, IQ3_M is 10.1 GB, Q3_K is 10.8 GB and 14 more.
What context length does Aurora Gem Opt lora8 mistral 22b model 15k grb support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.
Where can I download Aurora Gem Opt lora8 mistral 22b model 15k grb GGUF?
The files are on Hugging Face in the RichardErkhov/Aurora-Gem_-_Opt_lora8_mistral_22b_model_15k_grb-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.