Mars_27B_V.1 needs about 22.0 GB of memory at Q4_K_M (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 23.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
Mars_27B_V.1 – a 28.4B Gemma3 model focused on roleplay
Mars_27B_V.1 is a 28.4B parameter Gemma3 model merged from pre‑trained variants. It is tuned for complex roleplay scenarios and retains detailed context over long passages. The model supports Russian and has limited vision testing.
Good at
- Long‑form roleplay
- Detailed context retention
- Instruction following
Limits
- Large memory footprint – even Q4_K_S needs >21GB VRAM at 8k context
- No official license information
- Limited vision support
Best for
- Chatbot roleplay scripts
- Narrative generation
- Assistant tasks requiring deep context
Who it’s for. Developers building roleplay or narrative assistants who need a large context window and can allocate sufficient GPU memory. The model is suitable for users who can run GGUF files with llama.cpp and are comfortable managing quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 4.7 GB | Fits | Get file → | |
| IQ1_S | 6.7 GB | 11.4 GB | Too big | Get file → | |
| IQ1_M | 7.3 GB | 11.9 GB | Too big | Get file → | |
| IQ2_XXS | 8.1 GB | 12.8 GB | Too big | Get file → | |
| IQ2_XS | 8.9 GB | 13.6 GB | Too big | Get file → | |
| IQ2_S | 9.4 GB | 14.0 GB | Too big | Get file → | |
| IQ2_M | 10.1 GB | 14.8 GB | Too big | Get file → | |
| Q2_K_S | 10.2 GB | 14.9 GB | Too big | Get file → | |
| Q2_K | 11.0 GB | 15.6 GB | Too big | Get file → | |
| IQ3_XXS | 11.3 GB | 16.0 GB | Too big | Get file → | |
| IQ3_XS | 12.2 GB | 16.8 GB | Too big | Get file → | |
| IQ3_S | 12.8 GB | 17.4 GB | Too big | Get file → | |
| Q3_K_S | 12.8 GB | 17.4 GB | Too big | Get file → | |
| IQ3_M | 13.2 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_M | 14.0 GB | 18.7 GB | Too big | Get file → | |
| Q3_K_L | 15.1 GB | 19.8 GB | Too big | Get file → | |
| IQ4_XS | 15.5 GB | 20.2 GB | Too big | Get file → | |
| Q4_0 | 16.4 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_S | 16.5 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_M | 17.3 GB | 22.0 GB | Too big | Get file → | |
| Q4_1 | 18.0 GB | 22.7 GB | Too big | Get file → | |
| Q5_K_S | 19.7 GB | 24.4 GB | Too big | Get file → | |
| Q5_K_M | 20.2 GB | 24.9 GB | Too big | Get file → | |
| Q6_K | 23.3 GB | 28.0 GB | Too big | Get file → |
For 16GB VRAM, the smallest available quant is Q4_K_S (est. 21.1GB at 8k context) – it will not fit. For 24GB VRAM, Q4_K_S is suitable. For 32GB VRAM, consider Q5_K_M (est. 24.9GB) or Q6_K (est. 28GB).
What GPU do you need for Mars_27B_V.1?
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: the best quant that fits is the main file (0.0 GB file, about 4.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.7 GB in use).
- 12 GB VRAM: the best quant that fits is IQ1_M (7.3 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XXS (11.3 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (18.0 GB file, about 22.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (23.3 GB file, about 28.0 GB in use).
Which Mars_27B_V.1 quant should you choose?
Q4_K_M is the usual starting point for Mars_27B_V.1: it balances file size and quality well. Here it is a 17.3 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
Source
Frequently asked questions about Mars_27B_V.1
How much VRAM does Mars_27B_V.1 need?
About 22.0 GB at Q4_K_M with an 8K context window. That is the 17.3 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 Mars_27B_V.1 on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mars_27B_V.1 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 6.7 GB, IQ1_M is 7.3 GB, IQ2_XXS is 8.1 GB, IQ2_XS is 8.9 GB, IQ2_S is 9.4 GB and 18 more.
What context length does Mars_27B_V.1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.
Where can I download Mars_27B_V.1 GGUF?
The files are on Hugging Face in the mradermacher/Mars_27B_V.1-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 Mars_27B_V.1 on 8GB VRAM?
No, the smallest quant requires over 21GB VRAM at 8k context. 8GB is insufficient.
Does the model support vision tasks?
Vision support was briefly tested; functionality exists but is not fully documented.
What context length does the model support?
The model was trained on 131072 tokens and can handle up to that context length.