SmaugDolphin 34B slerp i1 needs about 18.8 GB of memory at Q4_K_M (a 16.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 6.1 GB (IQ1_S) to 22.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
SmaugDolphin 34B slerp i1 is a 27.7B-parameter Smaugdolphin model in GGUF format, quantized by mradermacher. Its trained context length is 195K tokens. The repository has 21 quant files, from 6.1 GB (IQ1_S) to 22.7 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 6.1 GB | 8.2 GB | Too big | Get file → | |
| IQ1_M | 6.6 GB | 8.8 GB | Too big | Get file → | |
| IQ2_XXS | 7.5 GB | 9.7 GB | Too big | Get file → | |
| IQ2_XS | 8.3 GB | 10.5 GB | Too big | Get file → | |
| IQ2_S | 8.8 GB | 10.9 GB | Too big | Get file → | |
| IQ2_M | 9.5 GB | 11.7 GB | Too big | Get file → | |
| Q2_K | 10.4 GB | 12.5 GB | Too big | Get file → | |
| IQ3_XXS | 10.8 GB | 12.9 GB | Too big | Get file → | |
| IQ3_XS | 11.5 GB | 13.6 GB | Too big | Get file → | |
| Q3_K_S | 12.1 GB | 14.2 GB | Too big | Get file → | |
| IQ3_S | 12.1 GB | 14.2 GB | Too big | Get file → | |
| IQ3_M | 12.6 GB | 14.7 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 15.6 GB | Too big | Get file → | |
| Q3_K_L | 14.6 GB | 16.7 GB | Too big | Get file → | |
| IQ4_XS | 14.9 GB | 17.0 GB | Too big | Get file → | |
| Q4_0 | 15.8 GB | 17.9 GB | Too big | Get file → | |
| Q4_K_S | 15.8 GB | 17.9 GB | Too big | Get file → | |
| Q4_K_M | 16.7 GB | 18.8 GB | Too big | Get file → | |
| Q5_K_S | 19.1 GB | 21.2 GB | Too big | Get file → | |
| Q5_K_M | 19.6 GB | 21.7 GB | Too big | Get file → | |
| Q6_K | 22.7 GB | 24.8 GB | Too big | Get file → |
What GPU do you need for SmaugDolphin 34B slerp i1?
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 IQ2_M (9.5 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_M (13.5 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.6 GB file, about 21.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.7 GB file, about 24.8 GB in use).
Which SmaugDolphin 34B slerp i1 quant should you choose?
Q4_K_M is the usual starting point for SmaugDolphin 34B slerp i1: it balances file size and quality well. Here it is a 16.7 GB file.
If memory is tight, the smallest file is IQ1_S at 6.1 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 SmaugDolphin 34B slerp i1
How much VRAM does SmaugDolphin 34B slerp i1 need?
About 18.8 GB at Q4_K_M with an 8K context window. That is the 16.7 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 SmaugDolphin 34B slerp i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SmaugDolphin 34B slerp i1 GGUF?
It depends on the quant: IQ1_S is 6.1 GB, IQ1_M is 6.6 GB, IQ2_XXS is 7.5 GB, IQ2_XS is 8.3 GB, IQ2_S is 8.8 GB, IQ2_M is 9.5 GB and 15 more.
What context length does SmaugDolphin 34B slerp i1 support?
The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download SmaugDolphin 34B slerp i1 GGUF?
The files are on Hugging Face in the mradermacher/SmaugDolphin-34B-slerp-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.