Llm Jp 4.1 32b A3B Thinking needs about 22.6 GB of memory at Q4_K_M (a 21.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 9 quants, from 12.6 GB (IQ2_S) to 34.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
32‑billion‑parameter Qwen3MoE LLM with 65k‑token context
Llm Jp 4.1 32b A3B Thinking is a transformer‑based language model built on the Qwen3MoE architecture. It contains 32 billion parameters, with 3 billion active parameters in the MoE. The model supports a 65 536‑token context window and is released under Apache‑2.0.
Good at
- Reasoning tasks
- Large context handling
- Japanese language support
Limits
- Requires high VRAM for full precision
- No vision or multimodal capabilities
- Uncensored content may be unsafe
Best for
- Research on reasoning models
- Testing large‑context inference
- Japanese NLP experiments
Who it’s for. Researchers and developers needing a large‑parameter, high‑context LLM for experimentation. The model is intended for research and safety studies only, not for production use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_S | 12.6 GB | 13.7 GB | Too big | Get file → | |
| IQ2_M | 13.3 GB | 14.3 GB | Too big | Get file → | |
| IQ3_XXS | 14.5 GB | 15.6 GB | Too big | Get file → | |
| IQ3_M | 15.7 GB | 16.8 GB | Too big | Get file → | |
| IQ4_XS | 17.7 GB | 18.7 GB | Too big | Get file → | |
| Q4_K_M | 21.5 GB | 22.6 GB | Too big | Get file → | |
| Q5_K_M | 24.5 GB | 25.6 GB | Too big | Get file → | |
| Q6_K | 29.0 GB | 30.0 GB | Too big | Get file → | |
| Q8_0 | 34.2 GB | 35.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_S (12.62 GB file, ~13.7 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (21.52 GB file, ~22.6 GB memory) offers a balance of size and performance. Higher quants such as Q6_K or Q8_0 require 28–35 GB VRAM.
What GPU do you need for Llm Jp 4.1 32b A3B Thinking?
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: the best quant that fits is IQ3_XXS (14.5 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.5 GB file, about 22.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (29.0 GB file, about 30.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (34.2 GB file, about 35.2 GB in use).
Which Llm Jp 4.1 32b A3B Thinking quant should you choose?
Q4_K_M is the usual starting point for Llm Jp 4.1 32b A3B Thinking: it balances file size and quality well. Here it is a 21.5 GB file.
The Q8_0 file is 34.2 GB, about 1.6 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 IQ2_S at 12.6 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 Llm Jp 4.1 32b A3B Thinking
How much VRAM does Llm Jp 4.1 32b A3B Thinking need?
About 22.6 GB at Q4_K_M with an 8K context window. That is the 21.5 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 Llm Jp 4.1 32b A3B Thinking on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llm Jp 4.1 32b A3B Thinking GGUF?
It depends on the quant: IQ2_S is 12.6 GB, IQ2_M is 13.3 GB, IQ3_XXS is 14.5 GB, IQ3_M is 15.7 GB, IQ4_XS is 17.7 GB, Q4_K_M is 21.5 GB and 3 more.
What context length does Llm Jp 4.1 32b A3B Thinking support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download Llm Jp 4.1 32b A3B Thinking GGUF?
The files are on Hugging Face in the OS-Software/llm-jp-4.1-32b-a3b-thinking-uncensored-heretic-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 Llm Jp 4.1 32b A3B Thinking 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 this model on 8 GB VRAM?
Use the IQ2_S quantized file; it requires about 13.7 GB of VRAM at 8k context, which is close to 8 GB but may need swapping.
Does this model support image input?
No, the model is purely text‑based and has no vision capabilities.
Is the model safe for public deployment?
The model has reduced safety alignment; it is intended for research only and should not be deployed in public services.