DictaLM 3.0 Nemotron 12B Instruct needs about 18.4 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 7.5 GB (Q4_K_M) to 24.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 41.6 GB.
DictaLM 3.0 Nemotron 12B Instruct – a 12‑billion‑parameter Hebrew‑English hybrid SSM model
DictaLM 3.0 Nemotron 12B Instruct is a 12.3‑billion‑parameter hybrid‑SSM instruct model. It is trained on Hebrew and English corpora and supports instruction following and tool‑calling. The model is available in several GGUF quantizations.
Good at
- Instruction following
- Tool‑calling
- Hebrew‑English text generation
Limits
- No vision support
- Large context requires high VRAM
- License is other
Best for
- Chatbots needing Hebrew support
- Tool‑integrated applications
- Research on bilingual LLMs
Who it’s for. Developers building Hebrew‑English chat or tool‑calling systems. Researchers exploring hybrid‑SSM architectures. Anyone needing a large, open‑weight model with instruction fine‑tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 7.5 GB | 18.4 GB | Too big | Get file → | |
| Q5_K_M | 8.8 GB | 19.7 GB | Too big | Get file → | |
| Q6_K | 10.1 GB | 21.0 GB | Too big | Get file → | |
| Q8_0 | 13.1 GB | 24.0 GB | Too big | Get file → | |
| BF16 | 24.6 GB | 35.5 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 7.49 GB, memory 18.4 GB at 8 k context). For 12 GB VRAM use Q5_K_M (8.76 GB, 19.7 GB). For 16 GB VRAM use Q6_K (10.11 GB, 21 GB).
What GPU do you need for DictaLM 3.0 Nemotron 12B Instruct?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q8_0 (13.1 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (13.1 GB file, about 24.0 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (24.6 GB file, about 35.5 GB in use).
Which DictaLM 3.0 Nemotron 12B Instruct quant should you choose?
Q4_K_M is the usual starting point for DictaLM 3.0 Nemotron 12B Instruct: it balances file size and quality well. Here it is a 7.5 GB file.
The Q8_0 file is 13.1 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about DictaLM 3.0 Nemotron 12B Instruct
How much VRAM does DictaLM 3.0 Nemotron 12B Instruct need?
About 18.4 GB at Q4_K_M with an 8K context window. That is the 7.5 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 DictaLM 3.0 Nemotron 12B Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DictaLM 3.0 Nemotron 12B Instruct GGUF?
It depends on the quant: Q4_K_M is 7.5 GB, Q5_K_M is 8.8 GB, Q6_K is 10.1 GB, Q8_0 is 13.1 GB, BF16 is 24.6 GB.
What context length does DictaLM 3.0 Nemotron 12B Instruct support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 10.4 GB at 8K and 41.6 GB at 32K.
Where can I download DictaLM 3.0 Nemotron 12B Instruct GGUF?
The files are on Hugging Face in the dicta-il/DictaLM-3.0-Nemotron-12B-Instruct-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 DictaLM 3.0 Nemotron 12B Instruct use?
Hugging Face lists the license as other. 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 DictaLM 3.0 on 8 GB VRAM?
Use the Q4_K_M quantization; it requires about 18.4 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does this model support vision tasks?
No, the model has no vision capabilities.
What is the context length of this model?
The model was trained on 1,048,576 tokens of context.