Mag Mell R1 21B Q5 K M needs about 17.3 GB of memory at Q5_K_M (a 14.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.
Mag Mell R1 21B Q5 K M is a 20.4B-parameter Mag model in GGUF format, quantized by Frowning. Its trained context length is 1000K tokens. The repository has 1 quant file, from 14.5 GB (Q5_K_M) to 14.5 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 14.5 GB | 17.3 GB | Too big | Get file → |
What GPU do you need for Mag Mell R1 21B Q5 K M?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q5_K_M (14.5 GB file, about 17.3 GB in use).
Which Mag Mell R1 21B Q5 K M quant should you choose?
Q5_K_M (14.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mag Mell R1 21B Q5 K M
How much VRAM does Mag Mell R1 21B Q5 K M need?
About 17.3 GB at Q5_K_M with an 8K context window. That is the 14.5 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 Mag Mell R1 21B Q5 K M on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mag Mell R1 21B Q5 K M GGUF?
It depends on the quant: Q5_K_M is 14.5 GB.
What context length does Mag Mell R1 21B Q5 K M 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 21B Q5 K M GGUF?
The files are on Hugging Face in the Frowning/Mag-Mell-R1-21B-Q5_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.