Undi95_Clover3 17B Base needs about 13.2 GB of memory at Q4_K_M (a 10.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 6.3 GB (Q2_K) to 17.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.2 GB.
Undi95_Clover3 17B Base is a 16.8B-parameter Clover model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 14 quant files, from 6.3 GB (Q2_K) to 17.9 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 6.3 GB | 9.3 GB | Too big | Get file → | |
| IQ3_XS | 6.9 GB | 10.0 GB | Too big | Get file → | |
| Q3_K_S | 7.3 GB | 10.3 GB | Too big | Get file → | |
| IQ3_S | 7.3 GB | 10.4 GB | Too big | Get file → | |
| IQ3_M | 7.6 GB | 10.6 GB | Too big | Get file → | |
| Q3_K_M | 8.1 GB | 11.2 GB | Too big | Get file → | |
| Q3_K_L | 8.9 GB | 11.9 GB | Too big | Get file → | |
| IQ4_XS | 9.1 GB | 12.2 GB | Too big | Get file → | |
| Q4_K_S | 9.6 GB | 12.6 GB | Too big | Get file → | |
| Q4_K_M | 10.1 GB | 13.2 GB | Too big | Get file → | |
| Q5_K_S | 11.6 GB | 14.6 GB | Too big | Get file → | |
| Q5_K_M | 11.9 GB | 15.0 GB | Too big | Get file → | |
| Q6_K | 13.8 GB | 16.9 GB | Too big | Get file → | |
| Q8_0 | 17.9 GB | 20.9 GB | Too big | Get file → |
What GPU do you need for Undi95_Clover3 17B Base?
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_L (8.9 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (11.9 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (17.9 GB file, about 20.9 GB in use).
Which Undi95_Clover3 17B Base quant should you choose?
Q4_K_M is the usual starting point for Undi95_Clover3 17B Base: it balances file size and quality well. Here it is a 10.1 GB file.
The Q8_0 file is 17.9 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 Q2_K at 6.3 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 Undi95_Clover3 17B Base
How much VRAM does Undi95_Clover3 17B Base need?
About 13.2 GB at Q4_K_M with an 8K context window. That is the 10.1 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 Undi95_Clover3 17B Base on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Undi95_Clover3 17B Base GGUF?
It depends on the quant: Q2_K is 6.3 GB, IQ3_XS is 6.9 GB, Q3_K_S is 7.3 GB, IQ3_S is 7.3 GB, IQ3_M is 7.6 GB, Q3_K_M is 8.1 GB and 8 more.
What context length does Undi95_Clover3 17B Base support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.6 GB at 8K and 10.2 GB at 32K.
Where can I download Undi95_Clover3 17B Base GGUF?
The files are on Hugging Face in the mradermacher/Clover3-17B-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 Undi95_Clover3 17B Base use?
Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.