ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B needs about 33.0 GB of memory at Q4_K_M (a 25.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 15 quants, from 0.1 GB to 34.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.
ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B – a 32.9B parameter model with efficient reasoning
ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B is a 32.9B parameter model built on the nemotron_h_moe architecture. It uses a mixture of experts with 3 active parameters and is trained on 1048576 context tokens. The model excels at reasoning and tool usage.
Good at
- Reasoning tasks
- Tool integration
- Large context handling
Limits
- No vision support
- License is other
- Requires large VRAM for full precision
Best for
- Enterprise inference with limited tokens
- Concurrent request handling
- Complex reasoning workflows
Who it’s for. Engineers and researchers needing a large, efficient reasoning model for server‑side deployment. The model is suitable for applications that require high context length and tool usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 7.7 GB | Tight | Get file → | |
| Q2_K | 18.7 GB | 26.3 GB | Too big | Get file → | |
| IQ3_S | 18.7 GB | 26.3 GB | Too big | Get file → | |
| Q3_K_S | 18.7 GB | 26.3 GB | Too big | Get file → | |
| IQ4_XS | 18.7 GB | 26.3 GB | Too big | Get file → | |
| Q4_0 | 18.8 GB | 26.4 GB | Too big | Get file → | |
| IQ3_M | 18.9 GB | 26.5 GB | Too big | Get file → | |
| Q3_K_M | 20.7 GB | 28.3 GB | Too big | Get file → | |
| Q4_1 | 20.8 GB | 28.4 GB | Too big | Get file → | |
| Q3_K_L | 21.6 GB | 29.2 GB | Too big | Get file → | |
| Q4_K_S | 22.8 GB | 30.4 GB | Too big | Get file → | |
| Q5_K_S | 24.8 GB | 32.4 GB | Too big | Get file → | |
| Q4_K_M | 25.4 GB | 33.0 GB | Too big | Get file → | |
| Q5_K_M | 27.0 GB | 34.7 GB | Too big | Get file → | |
| Q6_K | 34.9 GB | 42.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 18.81 GB, memory 26.4 GB at 8 k context). For 12 GB VRAM, Q4_K_S (22.84 GB, 30.4 GB) is a good balance. For 16 GB VRAM, Q5_K_M (27.04 GB, 34.7 GB) offers higher quality while staying within budget. Estimates are approximate.
What GPU do you need for ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B?
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 the main file (0.1 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.7 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_S (22.8 GB file, about 30.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (34.9 GB file, about 42.5 GB in use).
Which ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B quant should you choose?
Q4_K_M is the usual starting point for ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B: it balances file size and quality well. Here it is a 25.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B
How much VRAM does ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B need?
About 33.0 GB at Q4_K_M with an 8K context window. That is the 25.4 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 ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B GGUF?
It depends on the quant: file is 0.1 GB, Q2_K is 18.7 GB, IQ3_S is 18.7 GB, Q3_K_S is 18.7 GB, IQ4_XS is 18.7 GB, Q4_0 is 18.8 GB and 9 more.
What context length does ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B 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 7.1 GB at 8K and 28.5 GB at 32K.
Where can I download ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B GGUF?
The files are on Hugging Face in the mradermacher/ThinkingCap-NVIDIA-Nemotron-3.5-Lightning-30B-A3B-i1-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 ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B 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 this model on 8 GB VRAM?
Use the Q4_0 quant; it requires about 26.4 GB of VRAM at 8 k context, so 8 GB is insufficient for full inference.
Does this model support vision tasks?
No, the model has no vision capabilities.
What is the maximum context length?
The model was trained on 1048576 context tokens.