Mag Mell R1 Uncensored 21B needs about 15.2 GB of memory at Q4_K_M (a 12.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 0.0 GB to 16.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.
Mag Mell R1 Uncensored 21B – 20.4B llama model
Mag Mell R1 Uncensored 21B is a 20.4B parameter llama architecture model. It was quantized by mradermacher and offers reasoning capabilities. The model supports a context of up to 1,024,000 tokens.
Good at
- Reasoning
- Large context handling
- High parameter count
Limits
- No vision support
- License not specified
- Large VRAM required for full precision
Best for
- Complex reasoning tasks
- Long-form content generation
- Research prototyping
Who it’s for. Developers and researchers who need a large llama model with extensive context and reasoning abilities. The model is suitable for local deployment using llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.9 GB | Fits | Get file → | |
| IQ1_S | 4.7 GB | 7.6 GB | Tight | Get file → | |
| IQ1_M | 5.1 GB | 8.0 GB | Tight | Get file → | |
| IQ2_XXS | 5.8 GB | 8.6 GB | Too big | Get file → | |
| IQ2_XS | 6.3 GB | 9.2 GB | Too big | Get file → | |
| IQ2_S | 6.7 GB | 9.5 GB | Too big | Get file → | |
| IQ2_M | 7.2 GB | 10.0 GB | Too big | Get file → | |
| Q2_K_S | 7.3 GB | 10.1 GB | Too big | Get file → | |
| Q2_K | 7.8 GB | 10.6 GB | Too big | Get file → | |
| IQ3_XXS | 8.1 GB | 10.9 GB | Too big | Get file → | |
| IQ3_XS | 8.6 GB | 11.5 GB | Too big | Get file → | |
| Q3_K_S | 9.0 GB | 11.9 GB | Too big | Get file → | |
| IQ3_S | 9.1 GB | 11.9 GB | Too big | Get file → | |
| IQ3_M | 9.4 GB | 12.2 GB | Too big | Get file → | |
| Q3_K_M | 10.0 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_L | 10.8 GB | 13.7 GB | Too big | Get file → | |
| IQ4_XS | 11.1 GB | 14.0 GB | Too big | Get file → | |
| Q4_0 | 11.7 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_S | 11.7 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_M | 12.4 GB | 15.2 GB | Too big | Get file → | |
| Q4_1 | 12.9 GB | 15.8 GB | Too big | Get file → | |
| Q5_K_S | 14.1 GB | 17.0 GB | Too big | Get file → | |
| Q5_K_M | 14.5 GB | 17.3 GB | Too big | Get file → | |
| Q6_K | 16.8 GB | 19.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 4.72 GB, memory 7.6 GB). For 12 GB VRAM, use Q4_K_M (file size 12.36 GB, memory 15.2 GB). For 16 GB VRAM, use Q5_K_M (file size 14.5 GB, memory 17.3 GB). Memory estimates are approximate.
What GPU do you need for Mag Mell R1 Uncensored 21B?
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: the best quant that fits is the main file (0.0 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ1_M (5.1 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_S (9.1 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_1 (12.9 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (16.8 GB file, about 19.6 GB in use).
Which Mag Mell R1 Uncensored 21B quant should you choose?
Q4_K_M is the usual starting point for Mag Mell R1 Uncensored 21B: it balances file size and quality well. Here it is a 12.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Mag Mell R1 Uncensored 21B
How much VRAM does Mag Mell R1 Uncensored 21B need?
About 15.2 GB at Q4_K_M with an 8K context window. That is the 12.4 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 Mag Mell R1 Uncensored 21B on an 8 GB GPU?
Yes, with IQ1_M: the 5.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mag Mell R1 Uncensored 21B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 4.7 GB, IQ1_M is 5.1 GB, IQ2_XXS is 5.8 GB, IQ2_XS is 6.3 GB, IQ2_S is 6.7 GB and 18 more.
What context length does Mag Mell R1 Uncensored 21B 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 2.3 GB at 8K and 9.4 GB at 32K.
Where can I download Mag Mell R1 Uncensored 21B GGUF?
The files are on Hugging Face in the mradermacher/Mag-Mell-R1-Uncensored-21B-i1-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 this model on 8 GB VRAM?
Use the IQ1_S quant, which requires about 7.6 GB of VRAM at 8 k context.
Does this model support vision?
No, the model has no vision capabilities.
What is the maximum context length?
The model was trained with a context of 1,024,000 tokens.