TigerLLM 12B It needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 12.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
TigerLLM 12B It – Bangla instruction‑tuned LLM on Gemma3
TigerLLM 12B It is a 11.8 billion‑parameter model fine‑tuned on Bangla‑Instruct. It uses the Gemma 3 architecture and includes a vision encoder unchanged from the base model. The model is released under a CC‑BY‑4.0 license.
Good at
- Bangla instruction following
- Vision‑text multimodal tasks
- Instruction‑tuned generation
Limits
- No vision training on Bangla data
- Requires 8 k context for memory estimates
- No PEFT needed – LoRA merged
Best for
- Bangla content creation
- Multimodal QA in Bangla
- Instruction‑driven chatbots
Who it’s for. Developers building Bangla‑centric applications who need a ready‑to‑run instruction‑tuned model. The model is suitable for researchers and hobbyists who prefer a single GGUF file without separate base weights.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.8 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_M | 6.0 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_L | 6.5 GB | 10.2 GB | Too big | Get file → | |
| IQ4_XS | 6.6 GB | 10.3 GB | Too big | Get file → | |
| Q4_K_S | 6.9 GB | 10.7 GB | Too big | Get file → | |
| Q4_K_M | 7.3 GB | 11.0 GB | Too big | Get file → | |
| Q5_K_S | 8.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_M | 8.4 GB | 12.2 GB | Too big | Get file → | |
| Q6_K | 9.7 GB | 13.4 GB | Too big | Get file → | |
| Q8_0 | 12.5 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (4.77 GB, ~8.5 GB memory at 8 k context). For 16 GB VRAM Q4_K_M (7.3 GB, ~11 GB memory) is a good balance. For larger GPUs Q8_0 (12.51 GB, ~16.2 GB memory) offers full precision.
What GPU do you need for TigerLLM 12B It?
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 (8.2 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).
Which TigerLLM 12B It quant should you choose?
Q4_K_M is the usual starting point for TigerLLM 12B It: it balances file size and quality well. Here it is a 7.3 GB file.
The Q8_0 file is 12.5 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 Q2_K at 4.8 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 TigerLLM 12B It
How much VRAM does TigerLLM 12B It need?
About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 TigerLLM 12B It on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of TigerLLM 12B It GGUF?
It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.0 GB, Q3_K_L is 6.5 GB, IQ4_XS is 6.6 GB, Q4_K_S is 6.9 GB and 5 more.
What context length does TigerLLM 12B It 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 TigerLLM 12B It GGUF?
The files are on Hugging Face in the mradermacher/TigerLLM-12B-it-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does TigerLLM 12B It use?
Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run TigerLLM 12B It on 8 GB VRAM?
Yes, the Q2_K quant file is 4.77 GB and requires about 8.5 GB of VRAM at 8 k context, which fits an 8 GB GPU with some headroom.
Does the model support vision tasks?
The vision encoder is unchanged from Gemma 3 and was not trained on Bangla data, so vision performance may be limited.
What license applies to this model?
The model is released under a CC‑BY‑4.0 license, allowing reuse with attribution.