Merged RP Stew V2 51B i1 needs about 34.2 GB of memory at Q4_K_M (a 30.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 11.0 GB (IQ1_S) to 41.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 12.1 GB.
Merged RP Stew V2 51B i1 is a 51.1B-parameter Merged model in GGUF format, quantized by mradermacher. Its trained context length is 195K tokens. The repository has 21 quant files, from 11.0 GB (IQ1_S) to 41.9 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 11.0 GB | 14.5 GB | Too big | Get file → | |
| IQ1_M | 12.0 GB | 15.6 GB | Too big | Get file → | |
| IQ2_XXS | 13.7 GB | 17.3 GB | Too big | Get file → | |
| IQ2_XS | 15.2 GB | 18.7 GB | Too big | Get file → | |
| IQ2_S | 16.1 GB | 19.6 GB | Too big | Get file → | |
| IQ2_M | 17.4 GB | 21.0 GB | Too big | Get file → | |
| Q2_K | 19.0 GB | 22.5 GB | Too big | Get file → | |
| IQ3_XXS | 19.7 GB | 23.3 GB | Too big | Get file → | |
| IQ3_XS | 21.1 GB | 24.6 GB | Too big | Get file → | |
| Q3_K_S | 22.2 GB | 25.7 GB | Too big | Get file → | |
| IQ3_S | 22.2 GB | 25.8 GB | Too big | Get file → | |
| IQ3_M | 23.1 GB | 26.6 GB | Too big | Get file → | |
| Q3_K_M | 24.7 GB | 28.2 GB | Too big | Get file → | |
| Q3_K_L | 26.9 GB | 30.4 GB | Too big | Get file → | |
| IQ4_XS | 27.4 GB | 30.9 GB | Too big | Get file → | |
| Q4_0 | 29.0 GB | 32.5 GB | Too big | Get file → | |
| Q4_K_S | 29.1 GB | 32.6 GB | Too big | Get file → | |
| Q4_K_M | 30.7 GB | 34.2 GB | Too big | Get file → | |
| Q5_K_S | 35.2 GB | 38.7 GB | Too big | Get file → | |
| Q5_K_M | 36.1 GB | 39.7 GB | Too big | Get file → | |
| Q6_K | 41.9 GB | 45.5 GB | Too big | Get file → |
What GPU do you need for Merged RP Stew V2 51B 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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ1_M (12.0 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_XXS (19.7 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is IQ4_XS (27.4 GB file, about 30.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (41.9 GB file, about 45.5 GB in use).
Which Merged RP Stew V2 51B i1 quant should you choose?
Q4_K_M is the usual starting point for Merged RP Stew V2 51B i1: it balances file size and quality well. Here it is a 30.7 GB file.
If memory is tight, the smallest file is IQ1_S at 11.0 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 Merged RP Stew V2 51B i1
How much VRAM does Merged RP Stew V2 51B i1 need?
About 34.2 GB at Q4_K_M with an 8K context window. That is the 30.7 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 Merged RP Stew V2 51B i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Merged RP Stew V2 51B i1 GGUF?
It depends on the quant: IQ1_S is 11.0 GB, IQ1_M is 12.0 GB, IQ2_XXS is 13.7 GB, IQ2_XS is 15.2 GB, IQ2_S is 16.1 GB, IQ2_M is 17.4 GB and 15 more.
What context length does Merged RP Stew V2 51B 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 3.0 GB at 8K and 12.1 GB at 32K.
Where can I download Merged RP Stew V2 51B i1 GGUF?
The files are on Hugging Face in the mradermacher/Merged-RP-Stew-V2-51B-i1-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 Merged RP Stew V2 51B i1 use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.