NemoReRemix 12B needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 20 quants, from 4.4 GB (IQ2_M) to 49.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
NemoReRemix 12B – a 12.2B‑parameter storytelling and general assistant model
NemoReRemix 12B is a 12.2B‑parameter model built on the llama architecture. It merges several pre‑trained models to enhance storytelling, roleplay, and general assistance. The model supports ChatML and Mistral Instruct formats.
Good at
- Storytelling and roleplay
- General assistant tasks
- ChatML compatible interactions
Limits
- No vision support
- No license specified
- Large context requires high VRAM
Best for
- Creative writing prompts
- Interactive roleplay sessions
- General conversational AI
Who it’s for. Developers and hobbyists looking for a versatile large language model for text generation. It is suitable for users who can manage the memory requirements and want a model that performs well in storytelling and general assistance contexts.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 4.4 GB | 6.3 GB | Fits | Get file → | |
| Q2_K | 4.8 GB | 6.6 GB | Fits | Get file → | |
| IQ3_XS | 5.3 GB | 7.1 GB | Fits | Get file → | |
| Q2_K_L | 5.4 GB | 7.3 GB | Tight | Get file → | |
| Q3_K_S | 5.5 GB | 7.4 GB | Tight | Get file → | |
| IQ3_M | 5.7 GB | 7.6 GB | Tight | Get file → | |
| Q3_K_M | 6.1 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_L | 6.6 GB | 8.4 GB | Too big | Get file → | |
| IQ4_XS | 6.7 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_S | 7.1 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_XL | 7.1 GB | 9.0 GB | Too big | Get file → | |
| Q4_K_M | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q4_K_L | 8.0 GB | 9.8 GB | Too big | Get file → | |
| Q5_K_S | 8.5 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_M | 8.7 GB | 10.6 GB | Too big | Get file → | |
| Q5_K_L | 9.1 GB | 11.0 GB | Too big | Get file → | |
| Q6_K | 10.1 GB | 11.9 GB | Too big | Get file → | |
| Q6_K_L | 10.4 GB | 12.2 GB | Too big | Get file → | |
| Q8_0 | 13.0 GB | 14.9 GB | Too big | Get file → | |
| F32 | 49.0 GB | 50.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_M (file size 4.44 GB, estimated memory 6.3 GB) or Q2_K (4.79 GB, 6.6 GB). If 12 GB VRAM is available, Q4_K_M (7.48 GB, 9.3 GB) or Q5_K_M (8.73 GB, 10.6 GB) provide better quality. Higher‑precision quants such as Q8_0 or F32 require 14.9 GB or 50.8 GB respectively and are recommended only for systems with ample memory.
What GPU do you need for NemoReRemix 12B?
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: the best quant that fits is Q3_K_M (6.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
Which NemoReRemix 12B quant should you choose?
Q4_K_M is the usual starting point for NemoReRemix 12B: it balances file size and quality well. Here it is a 7.5 GB file.
The Q8_0 file is 13.0 GB, about 1.7 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 IQ2_M at 4.4 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 NemoReRemix 12B
How much VRAM does NemoReRemix 12B need?
About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 NemoReRemix 12B on an 8 GB GPU?
Yes, with Q3_K_M: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NemoReRemix 12B GGUF?
It depends on the quant: IQ2_M is 4.4 GB, Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q2_K_L is 5.4 GB, Q3_K_S is 5.5 GB, IQ3_M is 5.7 GB and 14 more.
What context length does NemoReRemix 12B support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download NemoReRemix 12B GGUF?
The files are on Hugging Face in the bartowski/NemoReRemix-12B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run NemoReRemix 12B on 8 GB VRAM?
Yes, using IQ2_M or Q2_K quantizations will fit within 8 GB VRAM, with estimated memory usage around 6.3–6.6 GB at 8 k context.
Does this model support vision tasks?
No, NemoReRemix 12B does not include vision capabilities.
What prompt format does it use?
The default prompt format is ChatML, but Mistral Instruct should also work theoretically.