Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 9 quants, from 11.5 GB (IQ2_M) to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive is a 34.7B-parameter Qwen model in GGUF format, quantized by mirxa2. Its trained context length is 256K tokens. The repository has 9 quant files, from 11.5 GB (IQ2_M) to 69.4 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 11.5 GB | 12.7 GB | Too big | Get file → | |
| IQ3_M | 15.4 GB | 16.6 GB | Too big | Get file → | |
| Q3_K_M | 16.8 GB | 17.9 GB | Too big | Get file → | |
| IQ4_XS | 18.7 GB | 19.8 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| Q5_K_M | 24.8 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 28.5 GB | 29.7 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → | |
| BF16 | 69.4 GB | 70.5 GB | Too big | Get file → |
What GPU do you need for Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive?
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 IQ2_M (11.5 GB file, about 12.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).
Which Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive quant should you choose?
Q4_K_M is the usual starting point for Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive: it balances file size and quality well. Here it is a 21.2 GB file.
The Q8_0 file is 36.9 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 11.5 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 Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive
How much VRAM does Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive GGUF?
It depends on the quant: IQ2_M is 11.5 GB, IQ3_M is 15.4 GB, Q3_K_M is 16.8 GB, IQ4_XS is 18.7 GB, Q4_K_M is 21.2 GB, Q5_K_M is 24.8 GB and 3 more.
What context length does Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive GGUF?
The files are on Hugging Face in the mirxa2/Mirxa-3.5-35B-A3B-Uncensored-Mirxa-Aggressive repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Mirxa 3.5 35B A3B Uncensored Mirxa Aggressive use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.