Qwen3 Next 384E Abliterated Instruct needs about 38.0 GB of memory at Q4_K_M (a 36.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 24 quants, from 0.3 GB to 49.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3 Next 384E Abliterated Instruct – 60.3B parameter LLM with tool support
This model is a 60.3B parameter Qwen3‑Next variant pruned to 384 experts. It is trained on a 262144 token context window and licensed under MIT. The model supports tool usage and is available in multiple GGUF quantizations.
Good at
- Tool‑oriented instruction following
- Long‑context reasoning up to 262144 tokens
- Large‑scale language generation
Limits
- No vision capabilities
- Requires large VRAM for higher‑quality quants
- License is MIT – no commercial restrictions
Best for
- Developers building chatbot assistants
- Researchers needing long‑context inference
- Tool‑integrated automation workflows
Who it’s for. Engineers and researchers who need a large‑parameter model with extended context and tool support. The model is suitable for local deployment using llama.cpp and can be run on GPUs with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 12.3 GB | 13.6 GB | Too big | Get file → | |
| IQ1_M | 13.7 GB | 15.0 GB | Too big | Get file → | |
| IQ2_XXS | 16.0 GB | 17.3 GB | Too big | Get file → | |
| IQ2_XS | 17.8 GB | 19.1 GB | Too big | Get file → | |
| IQ2_S | 17.9 GB | 19.3 GB | Too big | Get file → | |
| IQ2_M | 19.8 GB | 21.1 GB | Too big | Get file → | |
| Q2_K_S | 20.7 GB | 22.0 GB | Too big | Get file → | |
| Q2_K | 22.1 GB | 23.4 GB | Too big | Get file → | |
| IQ3_XXS | 23.3 GB | 24.7 GB | Too big | Get file → | |
| IQ3_XS | 24.8 GB | 26.1 GB | Too big | Get file → | |
| Q3_K_S | 26.2 GB | 27.5 GB | Too big | Get file → | |
| IQ3_S | 26.2 GB | 27.5 GB | Too big | Get file → | |
| IQ3_M | 26.6 GB | 27.9 GB | Too big | Get file → | |
| Q3_K_M | 29.0 GB | 30.3 GB | Too big | Get file → | |
| Q3_K_L | 31.3 GB | 32.6 GB | Too big | Get file → | |
| IQ4_XS | 32.3 GB | 33.6 GB | Too big | Get file → | |
| Q4_0 | 34.3 GB | 35.6 GB | Too big | Get file → | |
| Q4_K_S | 34.5 GB | 35.8 GB | Too big | Get file → | |
| Q4_K_M | 36.7 GB | 38.0 GB | Too big | Get file → | |
| Q4_1 | 37.9 GB | 39.2 GB | Too big | Get file → | |
| Q5_K_S | 41.7 GB | 43.0 GB | Too big | Get file → | |
| Q5_K_M | 43.0 GB | 44.3 GB | Too big | Get file → | |
| Q6_K | 49.6 GB | 50.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (12.31 GB file, 13.6 GB memory) or IQ1_M (13.67 GB file, 15 GB memory). For 12 GB VRAM, IQ2_XXS (15.95 GB file, 17.3 GB memory) or IQ2_XS (17.78 GB file, 19.1 GB memory) are suitable. Higher‑quality quants such as Q4_K_M (36.73 GB file, 38 GB memory) require 40 GB+ VRAM.
What GPU do you need for Qwen3 Next 384E Abliterated 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: the best quant that fits is the main file (0.3 GB file, about 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.6 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ1_M (13.7 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q2_K (22.1 GB file, about 23.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q3_K_M (29.0 GB file, about 30.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (43.0 GB file, about 44.3 GB in use).
Which Qwen3 Next 384E Abliterated Instruct quant should you choose?
Q4_K_M is the usual starting point for Qwen3 Next 384E Abliterated Instruct: it balances file size and quality well. Here it is a 36.7 GB file.
If memory is tight, the smallest file is the first one in the table at 0.3 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 Qwen3 Next 384E Abliterated Instruct
How much VRAM does Qwen3 Next 384E Abliterated Instruct need?
About 38.0 GB at Q4_K_M with an 8K context window. That is the 36.7 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 Qwen3 Next 384E Abliterated Instruct on an 8 GB GPU?
Yes, with the smaller files: the 0.3 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3 Next 384E Abliterated Instruct GGUF?
It depends on the quant: file is 0.3 GB, IQ1_S is 12.3 GB, IQ1_M is 13.7 GB, IQ2_XXS is 16.0 GB, IQ2_XS is 17.8 GB, IQ2_S is 17.9 GB and 18 more.
What context length does Qwen3 Next 384E Abliterated Instruct support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download Qwen3 Next 384E Abliterated Instruct GGUF?
The files are on Hugging Face in the mradermacher/Qwen3-Next-384E-Abliterated-Instruct-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 Qwen3 Next 384E Abliterated Instruct use?
Hugging Face lists the license as mit. 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?
Yes, with the IQ1_S or IQ1_M quant, which use 13.6 GB and 15 GB of VRAM respectively at 8k context.
Does this model support image input?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the MIT license.