DopeorNope SOLARC MOE 10.7Bx6 needs about 34.2 GB of memory at Q4_K_M (a 32.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 17 quants, from 19.3 GB (Q2_K) to 36.5 GB (Q5_K_S).
DopeorNope SOLARC MOE 10.7Bx6 is a 53B-parameter Dopeornope model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 17 quant files, from 19.3 GB (Q2_K) to 36.5 GB (Q5_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 19.3 GB | 20.6 GB | Too big | Get file → | |
| IQ3_XS | 21.6 GB | 22.9 GB | Too big | Get file → | |
| Q3_K_S | 22.8 GB | 24.1 GB | Too big | Get file → | |
| IQ3_S | 22.9 GB | 24.2 GB | Too big | Get file → | |
| IQ3_M | 23.3 GB | 24.6 GB | Too big | Get file → | |
| Q3_K | 25.3 GB | 26.7 GB | Too big | Get file → | |
| Q3_K_M | 25.3 GB | 26.7 GB | Too big | Get file → | |
| Q3_K_L | 27.5 GB | 28.8 GB | Too big | Get file → | |
| IQ4_XS | 28.6 GB | 29.9 GB | Too big | Get file → | |
| Q4_0 | 29.9 GB | 31.2 GB | Too big | Get file → | |
| Q4_K_S | 30.1 GB | 31.4 GB | Too big | Get file → | |
| IQ4_NL | 30.1 GB | 31.5 GB | Too big | Get file → | |
| Q4_K | 32.1 GB | 33.4 GB | Too big | Get file → | |
| Q4_K_M | 32.1 GB | 33.4 GB | Too big | Get file → | |
| Q4_1 | 33.2 GB | 34.5 GB | Too big | Get file → | |
| Q5_0 | 36.5 GB | 37.8 GB | Too big | Get file → | |
| Q5_K_S | 36.5 GB | 37.8 GB | Too big | Get file → |
What GPU do you need for DopeorNope SOLARC MOE 10.7Bx6?
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 IQ3_XS (21.6 GB file, about 23.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_0 (29.9 GB file, about 32.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_0 (36.5 GB file, about 38.6 GB in use).
Which DopeorNope SOLARC MOE 10.7Bx6 quant should you choose?
Q4_K_M is the usual starting point for DopeorNope SOLARC MOE 10.7Bx6: it balances file size and quality well. Here it is a 32.1 GB file.
If memory is tight, the smallest file is Q2_K at 19.3 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 DopeorNope SOLARC MOE 10.7Bx6
How much VRAM does DopeorNope SOLARC MOE 10.7Bx6 need?
About 34.2 GB at Q4_K_M with an 8K context window. That is the 32.1 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 DopeorNope SOLARC MOE 10.7Bx6 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DopeorNope SOLARC MOE 10.7Bx6 GGUF?
It depends on the quant: Q2_K is 19.3 GB, IQ3_XS is 21.6 GB, Q3_K_S is 22.8 GB, IQ3_S is 22.9 GB, IQ3_M is 23.3 GB, Q3_K is 25.3 GB and 11 more.
What context length does DopeorNope SOLARC MOE 10.7Bx6 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.
Where can I download DopeorNope SOLARC MOE 10.7Bx6 GGUF?
The files are on Hugging Face in the RichardErkhov/DopeorNope_-_SOLARC-MOE-10.7Bx6-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 DopeorNope SOLARC MOE 10.7Bx6 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.