Gaja v1.00 needs about 9.0 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 2.6 GB (Q2_K) to 13.7 GB (F16).
Gaja v1.00 – a Hindi/Hinglish chat model based on OpenHathi
Gaja v1.00 is a 6.87B llama model fine‑tuned for conversational use in Hindi and Hinglish. It was trained on 1k samples and inherits the base OpenHathi architecture. The model is available in multiple GGUF quantizations.
Good at
- Conversational chat in Hindi and Hinglish
- Fine‑tuned for chat interactions
- Supports 4096 token context
Limits
- No vision support
- License is llama2
- No explicit language list beyond Hindi/Hinglish
Best for
- Chatbots for Hindi/Hinglish users
- Experimentation with conversational LLMs
- Local inference with GGUF
Who it’s for. Developers building Hindi or Hinglish chat applications who need a lightweight, locally runnable model. Researchers wanting to experiment with fine‑tuned conversational models on a llama architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.6 GB | 5.3 GB | Fits | Get file → | |
| Q3_K_S | 3.0 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_M | 3.4 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_L | 3.7 GB | 6.3 GB | Fits | Get file → | |
| IQ4_XS | 3.7 GB | 6.4 GB | Fits | Get file → | |
| Q4_K_S | 3.9 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_M | 4.2 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_S | 4.8 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 4.9 GB | 7.5 GB | Tight | Get file → | |
| Q6_K | 5.6 GB | 8.3 GB | Too big | Get file → | |
| Q8_0 | 7.3 GB | 9.9 GB | Too big | Get file → | |
| F16 | 13.7 GB | 16.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 4.17 GB, estimated 9 GB memory). For 12 GB VRAM, Q6_K (5.64 GB, 10.4 GB memory) or Q8_0 (7.3 GB, 12.1 GB memory) are suitable. For 18 GB VRAM, F16 (13.74 GB, 18.5 GB memory) provides full precision.
What GPU do you need for Gaja v1.00?
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: the best quant that fits is Q3_K_S (3.0 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (5.6 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (7.3 GB file, about 12.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (13.7 GB file, about 18.5 GB in use).
Which Gaja v1.00 quant should you choose?
Q4_K_M is the usual starting point for Gaja v1.00: it balances file size and quality well. Here it is a 4.2 GB file.
The Q8_0 file is 7.3 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 2.6 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 Gaja v1.00
How much VRAM does Gaja v1.00 need?
About 9.0 GB at Q4_K_M with an 8K context window. That is the 4.2 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 Gaja v1.00 on an 8 GB GPU?
Yes, with Q3_K_S: the 3.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gaja v1.00 GGUF?
It depends on the quant: Q2_K is 2.6 GB, Q3_K_S is 3.0 GB, Q3_K_M is 3.4 GB, Q3_K_L is 3.7 GB, IQ4_XS is 3.7 GB, Q4_K_S is 3.9 GB and 6 more.
What context length does Gaja v1.00 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download Gaja v1.00 GGUF?
The files are on Hugging Face in the mradermacher/Gaja-v1.00-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 Gaja v1.00 use?
Hugging Face lists the license as llama2. 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 Gaja v1.00 on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 9 GB memory at 8k context, which fits an 8 GB VRAM setup with some overhead.
Does Gaja support English?
The model is fine‑tuned for Hindi and Hinglish; English support is not guaranteed.
Where can I download the GGUF files?
GGUF files are available at the Huggingface repository mradermacher/Gaja-v1.00-GGUF.