ThinkingCap Nemotron 3.5 Lightning 30B A3B Abliterated 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 11 quants, from 18.7 GB (Q2_K) to 35.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.
ThinkingCap Nemotron 3.5 Lightning 30B A3B Abliterated – a 32.9B parameter mixture of experts model
This model is a 32.9B parameter Nemotron 3.5 Lightning variant with 3.0B active experts. It was fine‑tuned with shorter thinking traces and has no refusal behaviour. The model supports reasoning and tool use.
Good at
- Reasoning
- Tool calling
- Long‑context generation
Limits
- Mixture of experts requires large VRAM
- No vision support
- License is other
Best for
- Complex reasoning tasks
- Automated tool workflows
- Long‑form content creation
Who it’s for. Developers and researchers needing a large, expert‑based language model with reasoning and tool‑calling capabilities. The model is suitable for applications that can provide sufficient GPU memory for the mixture of experts architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 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 | 19.0 GB | 26.6 GB | Too big | Get file → | |
| Q3_K_M | 20.7 GB | 28.3 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 → | |
| Q8_0 | 35.0 GB | 42.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K or Q3_K_S (file size 18.66 GB or 18.68 GB, estimated memory 26.3 GB). For 16 GB VRAM, Q4_K_S (22.84 GB, 30.4 GB memory) or Q4_K_M (25.43 GB, 33 GB memory) are suitable. For 24 GB VRAM, Q5_K_M (27.04 GB, 34.7 GB memory) or Q6_K (34.92 GB, 42.5 GB memory) can be considered.
What GPU do you need for ThinkingCap Nemotron 3.5 Lightning 30B A3B Abliterated?
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: no quant fits at an 8K context.
- 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 Q8_0 (35.0 GB file, about 42.6 GB in use).
Which ThinkingCap Nemotron 3.5 Lightning 30B A3B Abliterated quant should you choose?
Q4_K_M is the usual starting point for ThinkingCap Nemotron 3.5 Lightning 30B A3B Abliterated: it balances file size and quality well. Here it is a 25.4 GB file.
The Q8_0 file is 35.0 GB, about 1.4 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 18.7 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
Frequently asked questions about ThinkingCap Nemotron 3.5 Lightning 30B A3B Abliterated
How much VRAM does ThinkingCap Nemotron 3.5 Lightning 30B A3B Abliterated 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 Nemotron 3.5 Lightning 30B A3B Abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ThinkingCap Nemotron 3.5 Lightning 30B A3B Abliterated GGUF?
It depends on the quant: Q2_K is 18.7 GB, Q3_K_S is 18.7 GB, IQ4_XS is 19.0 GB, Q3_K_M is 20.7 GB, Q3_K_L is 21.6 GB, Q4_K_S is 22.8 GB and 5 more.
What context length does ThinkingCap Nemotron 3.5 Lightning 30B A3B Abliterated 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 Nemotron 3.5 Lightning 30B A3B Abliterated GGUF?
The files are on Hugging Face in the mradermacher/ThinkingCap-Nemotron-3.5-Lightning-30B-A3B-abliterated-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 Nemotron 3.5 Lightning 30B A3B Abliterated 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?
The smallest quant files are Q2_K and Q3_K_S, each 18.66 GB and 18.68 GB. They require about 26.3 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.
Does this model support vision?
No, the model does not include vision capabilities.
What is the maximum context length?
The model was trained with 1,048,576 tokens and supports up to that context length.