Index Homura 2B needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.0 GB (Q2_K) to 3.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
Index Homura 2B – a 2B‑parameter translation model with syllable‑count control
Index Homura 2B is a 1.94B‑parameter model built on Qwen3.5. It translates text while respecting an explicit target syllable count and optional glossary constraints. The model is released under the apache‑2.0 license and supports vision tasks.
Good at
- Syllable‑controlled translation
- Glossary‑aware output
- Multilingual support
Limits
- No vision support in inference
- Requires CUDA GPU for vLLM
- Large context length 262144 tokens
Best for
- Creating timed subtitles
- Dubbing scripts with exact syllable limits
- Glossary‑restricted translations
Who it’s for. Developers and content creators needing precise syllable control in translations. The model is suitable for subtitle production, dubbing, and any scenario where word count must match a target.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.0 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_L | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ4_XS | 1.2 GB | 2.2 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 2.2 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q5_K_S | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q8_0 | 2.1 GB | 3.0 GB | Fits | Get file → | |
| F16 | 3.9 GB | 4.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_S (1.25 GB file, ~2.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (1.45 GB file, ~2.4 GB memory) offers higher quality. For 16 GB VRAM, Q6_K (1.61 GB file, ~2.5 GB memory) provides a balance of size and performance.
What GPU do you need for Index Homura 2B?
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: the best quant that fits is Q8_0 (2.1 GB file, about 3.0 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.9 GB file, about 4.8 GB in use).
Which Index Homura 2B quant should you choose?
Q4_K_M is the usual starting point for Index Homura 2B: it balances file size and quality well. Here it is a 1.3 GB file.
The Q8_0 file is 2.1 GB, about 1.6 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 1.0 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 Index Homura 2B
How much VRAM does Index Homura 2B need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Index Homura 2B on an 8 GB GPU?
Yes, with F16: the 3.9 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Index Homura 2B GGUF?
It depends on the quant: Q2_K is 1.0 GB, Q3_K_S is 1.0 GB, Q3_K_M is 1.1 GB, Q3_K_L is 1.2 GB, IQ4_XS is 1.2 GB, Q4_K_S is 1.2 GB and 6 more.
What context length does Index Homura 2B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.
Where can I download Index Homura 2B GGUF?
The files are on Hugging Face in the mradermacher/Index-Homura-2B-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 Index Homura 2B 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.
Can I run Index Homura 2B on 8 GB VRAM?
Yes, the Q4_K_S quant uses about 2.2 GB of VRAM at 8k context, leaving room for the model and KV cache.
Does the model support vision tasks?
The model detects vision abilities, but inference requires a CUDA GPU and vLLM; vision support is not included in the GGUF files.
What license applies to this model?
The model is released under the apache‑2.0 license, allowing free use and modification.