Mantra 14B needs about 11.1 GB of memory at Q4_K_M (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 5.6 GB (Q2_K) to 15.6 GB (Q8_0).
Mantra 14B – 14.7B parameter bilingual LLM for Hindi and English
Mantra 14B is a 14.7B parameter instruction‑tuned model optimized for Hindi and English. It is trained on a mixed language dataset and licensed under Apache‑2.0. The model supports a 16384 token context window.
Good at
- Hindi and English instruction following
- Large context handling
- Low emissions compared to baseline
Limits
- No vision support
- Requires 8‑k context for memory estimates
- No bias mitigation beyond training
Best for
- Chatbots in Hindi and English
- Content generation for bilingual audiences
- Fine‑tuning on regional datasets
Who it’s for. Developers building multilingual applications that need robust Hindi and English support. Researchers interested in bilingual LLM performance. Enterprises requiring an open‑source model under Apache‑2.0.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.6 GB | 7.8 GB | Tight | Get file → | |
| Q3_K_S | 6.5 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_M | 7.2 GB | 9.4 GB | Too big | Get file → | |
| Q3_K_L | 7.8 GB | 10.0 GB | Too big | Get file → | |
| IQ4_XS | 8.1 GB | 10.2 GB | Too big | Get file → | |
| Q4_K_S | 8.4 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_M | 8.9 GB | 11.1 GB | Too big | Get file → | |
| Q5_K_S | 10.2 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_M | 10.4 GB | 12.6 GB | Too big | Get file → | |
| Q6_K | 12.0 GB | 14.2 GB | Too big | Get file → | |
| Q8_0 | 15.6 GB | 17.8 GB | Too big | Get file → |
For 8‑GB VRAM, use Q2_K (5.61 GB, 7.8 GB memory). For 12‑GB VRAM, Q4_K_M (8.89 GB, 11.1 GB memory) or Q5_K_M (10.41 GB, 12.6 GB memory). For 16‑GB VRAM, Q6_K (12.03 GB, 14.2 GB memory) or Q8_0 (15.58 GB, 17.8 GB memory). Estimates are approximate.
What GPU do you need for Mantra 14B?
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 Q2_K (5.6 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (8.9 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.6 GB file, about 17.8 GB in use).
Which Mantra 14B quant should you choose?
Q4_K_M is the usual starting point for Mantra 14B: it balances file size and quality well. Here it is a 8.9 GB file.
The Q8_0 file is 15.6 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 at 5.6 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 Mantra 14B
How much VRAM does Mantra 14B need?
About 11.1 GB at Q4_K_M with an 8K context window. That is the 8.9 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 Mantra 14B on an 8 GB GPU?
Yes, with Q2_K: the 5.6 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 Mantra 14B GGUF?
It depends on the quant: Q2_K is 5.6 GB, Q3_K_S is 6.5 GB, Q3_K_M is 7.2 GB, Q3_K_L is 7.8 GB, IQ4_XS is 8.1 GB, Q4_K_S is 8.4 GB and 5 more.
What context length does Mantra 14B support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.7 GB at 8K and 3.4 GB at 16K.
Where can I download Mantra 14B GGUF?
The files are on Hugging Face in the mradermacher/Mantra-14B-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 Mantra 14B 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 Mantra 14B on 8 GB VRAM?
Yes, the Q2_K quant file is 5.61 GB and requires about 7.8 GB VRAM at 8‑k context.
Does Mantra 14B support vision tasks?
No, the model is purely text‑based and has no vision capabilities.