Tigerlily R3 needs about 10.7 GB of memory at Q4_K_M (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 19 quants, from 4.5 GB (Q2_K_S) to 23.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Tigerlily R3 – 11.8B Gemma3 model with vision support
Tigerlily R3 is an 11.8B parameter Gemma3 model merged from multiple pre‑trained sources. It supports vision tasks and offers a large 131072 token context window. The model is available in several GGUF quantizations.
Good at
- Vision and text tasks
- Large context handling
- Low‑memory quantizations
Limits
- No license specified
- No explicit language support listed
- Requires 8k context for memory estimates
Best for
- Image captioning
- Long‑form document analysis
- Multimodal chat
Who it’s for. Developers building multimodal applications that need a balance of performance and memory efficiency. The model is suitable for users with moderate GPU resources who can run GGUF files via llama.cpp or Ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_S | 4.5 GB | 8.2 GB | Too big | Get file → | |
| Q2_K | 4.6 GB | 8.4 GB | Too big | Get file → | |
| Q2_K_M | 4.8 GB | 8.5 GB | Too big | Get file → | |
| Q2_K_L | 5.0 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_S | 5.3 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_M | 5.7 GB | 9.4 GB | Too big | Get file → | |
| Q3_K_L | 6.3 GB | 10.0 GB | Too big | Get file → | |
| Q4_K_S | 6.7 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_M | 6.9 GB | 10.7 GB | Too big | Get file → | |
| Q4_K_XL | 7.5 GB | 11.3 GB | Too big | Get file → | |
| Q3_K_XL | 7.7 GB | 11.4 GB | Too big | Get file → | |
| Q5_K_S | 8.1 GB | 11.8 GB | Too big | Get file → | |
| Q5_K_M | 8.5 GB | 12.2 GB | Too big | Get file → | |
| Q5_K_XL | 8.7 GB | 12.4 GB | Too big | Get file → | |
| Q6_K | 9.7 GB | 13.4 GB | Too big | Get file → | |
| Q6_K_L | 9.9 GB | 13.6 GB | Too big | Get file → | |
| Q6_K_XL | 10.8 GB | 14.6 GB | Too big | Get file → | |
| Q8_0 | 12.5 GB | 16.2 GB | Too big | Get file → | |
| BF16 | 23.5 GB | 27.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (6.94 GB file, ~10.7 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (8.48 GB file, ~12.2 GB memory). Higher precision like BF16 requires 23.54 GB file and ~27.3 GB memory, suitable for large‑memory systems.
What GPU do you need for Tigerlily R3?
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: the best quant that fits is Q5_K_S (8.1 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K_XL (10.8 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (23.5 GB file, about 27.3 GB in use).
Which Tigerlily R3 quant should you choose?
Q4_K_M is the usual starting point for Tigerlily R3: it balances file size and quality well. Here it is a 6.9 GB file.
The Q8_0 file is 12.5 GB, about 1.8 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 Q2_K_S at 4.5 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 Tigerlily R3
How much VRAM does Tigerlily R3 need?
About 10.7 GB at Q4_K_M with an 8K context window. That is the 6.9 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 Tigerlily R3 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Tigerlily R3 GGUF?
It depends on the quant: Q2_K_S is 4.5 GB, Q2_K is 4.6 GB, Q2_K_M is 4.8 GB, Q2_K_L is 5.0 GB, Q3_K_S is 5.3 GB, Q3_K_M is 5.7 GB and 13 more.
What context length does Tigerlily R3 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download Tigerlily R3 GGUF?
The files are on Hugging Face in the EnlistedGhost/Tigerlily-R3-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 Tigerlily R3 on 8 GB VRAM?
Yes, the Q4_K_M quantization file is 6.94 GB and estimates ~10.7 GB memory at 8k context, which fits within 8 GB VRAM with some overhead.
Does Tigerlily R3 support vision tasks?
Yes, the model has detected vision abilities and can process image inputs.
What is the context length of Tigerlily R3?
The model supports a context length of 131072 tokens.