clown-70x1B needs about 33.0 GB of memory at Q4_K_M (a 32.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 20 quants, from 19.5 GB (Q2_K) to 40.2 GB (Q5_1).
clown-70x1B is a 53.6B-parameter Clown model in GGUF format, quantized by RichardErkhov. Its trained context length is 2K tokens. The repository has 20 quant files, from 19.5 GB (Q2_K) to 40.2 GB (Q5_1).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 19.5 GB | 20.0 GB | Too big | Get file → | |
| IQ3_XS | 21.8 GB | 22.3 GB | Too big | Get file → | |
| Q3_K_S | 23.1 GB | 23.6 GB | Too big | Get file → | |
| IQ3_S | 23.1 GB | 23.6 GB | Too big | Get file → | |
| IQ3_M | 23.3 GB | 23.9 GB | Too big | Get file → | |
| Q3_K | 25.6 GB | 26.1 GB | Too big | Get file → | |
| Q3_K_M | 25.6 GB | 26.1 GB | Too big | Get file → | |
| Q3_K_L | 27.7 GB | 28.2 GB | Too big | Get file → | |
| IQ4_XS | 28.8 GB | 29.3 GB | Too big | Get file → | |
| Q4_0 | 30.2 GB | 30.7 GB | Too big | Get file → | |
| Q4_K_S | 30.4 GB | 30.9 GB | Too big | Get file → | |
| IQ4_NL | 30.4 GB | 30.9 GB | Too big | Get file → | |
| Q4_K | 32.3 GB | 32.8 GB | Too big | Get file → | |
| Q4_K_M | 32.3 GB | 32.8 GB | Too big | Get file → | |
| Q4_1 | 33.5 GB | 34.1 GB | Too big | Get file → | |
| Q5_0 | 36.9 GB | 37.4 GB | Too big | Get file → | |
| Q5_K_S | 36.9 GB | 37.4 GB | Too big | Get file → | |
| Q5_K | 38.0 GB | 38.5 GB | Too big | Get file → | |
| Q5_K_M | 38.0 GB | 38.5 GB | Too big | Get file → | |
| Q5_1 | 40.2 GB (2 parts) | 40.8 GB | Too big | Get file → |
What GPU do you need for clown-70x1B?
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_M (23.3 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is IQ4_NL (30.4 GB file, about 31.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_1 (40.2 GB file, about 40.9 GB in use).
Which clown-70x1B quant should you choose?
Q4_K_M is the usual starting point for clown-70x1B: it balances file size and quality well. Here it is a 32.3 GB file.
If memory is tight, the smallest file is Q2_K at 19.5 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 clown-70x1B
How much VRAM does clown-70x1B need?
About 33.0 GB at Q4_K_M with an 8K context window. That is the 32.3 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 clown-70x1B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of clown-70x1B GGUF?
It depends on the quant: Q2_K is 19.5 GB, IQ3_XS is 21.8 GB, Q3_K_S is 23.1 GB, IQ3_S is 23.1 GB, IQ3_M is 23.3 GB, Q3_K is 25.6 GB and 14 more.
What context length does clown-70x1B support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.
Where can I download clown-70x1B GGUF?
The files are on Hugging Face in the RichardErkhov/BlouseJury_-_clown-70x1B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.