Gpt Oss 46b needs about 35.4 GB of memory at Q4_K_M (a 34.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 25 quants, from 0.0 GB to 48.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
45.7B‑parameter GPT‑OSS model with MoE and 131072‑token context
Gpt Oss 46b is a 45.7B‑parameter GPT‑OSS model that supports a 131072‑token context window. It is released under the Apache‑2.0 license and includes mixture‑of‑experts weights. The model is available in a variety of GGUF quantizations.
Good at
- Large context reasoning
- Fine‑tuning flexibility
- Agentic function calling
Limits
- Requires 16GB+ VRAM for MXFP4_MOE
- No vision support
- Large file sizes for high‑quality quants
Best for
- Long‑form content generation
- Custom fine‑tuning projects
- Chatbot back‑ends
Who it’s for. Developers and researchers who need a large‑context LLM with an open license and the ability to fine‑tune or run agentic tasks. The model is suitable for commercial deployment where copyleft restrictions are a concern.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| MXFP4_MOE | 25.8 GB | 26.7 GB | Too big | Get file → | |
| IQ1_M | 26.1 GB | 27.0 GB | Too big | Get file → | |
| IQ1_S | 26.1 GB | 27.0 GB | Too big | Get file → | |
| IQ2_XXS | 26.1 GB | 27.0 GB | Too big | Get file → | |
| IQ2_XS | 26.1 GB | 27.0 GB | Too big | Get file → | |
| Q3_K_S | 26.1 GB | 27.0 GB | Too big | Get file → | |
| IQ2_M | 26.2 GB | 27.1 GB | Too big | Get file → | |
| IQ2_S | 26.2 GB | 27.1 GB | Too big | Get file → | |
| IQ3_S | 26.2 GB | 27.1 GB | Too big | Get file → | |
| IQ3_XS | 26.2 GB | 27.1 GB | Too big | Get file → | |
| IQ3_XXS | 26.2 GB | 27.1 GB | Too big | Get file → | |
| Q2_K | 26.2 GB | 27.1 GB | Too big | Get file → | |
| IQ4_XS | 26.2 GB | 27.1 GB | Too big | Get file → | |
| Q4_0 | 26.3 GB | 27.2 GB | Too big | Get file → | |
| Q2_K_S | 26.3 GB | 27.2 GB | Too big | Get file → | |
| IQ3_M | 26.4 GB | 27.3 GB | Too big | Get file → | |
| Q3_K_M | 28.0 GB | 28.9 GB | Too big | Get file → | |
| Q3_K_L | 29.0 GB | 29.9 GB | Too big | Get file → | |
| Q4_1 | 29.0 GB | 29.9 GB | Too big | Get file → | |
| Q4_K_S | 31.9 GB | 32.8 GB | Too big | Get file → | |
| Q4_K_M | 34.5 GB | 35.4 GB | Too big | Get file → | |
| Q5_K_S | 34.6 GB | 35.5 GB | Too big | Get file → | |
| Q5_K_M | 36.8 GB | 37.7 GB | Too big | Get file → | |
| Q6_K | 48.5 GB | 49.4 GB | Too big | Get file → |
For 8‑GB VRAM, use the 0.04‑GB unknown quant. For 16‑GB VRAM, the MXFP4_MOE quant (25.77‑GB, 26.7‑GB memory at 8k context) is recommended. For 32‑GB VRAM, the Q4_K_S quant (31.87‑GB, 32.8‑GB memory) offers a good balance of size and quality.
What GPU do you need for Gpt Oss 46b?
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 (0.0 GB file, about 0.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_1 (29.0 GB file, about 29.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (36.8 GB file, about 37.7 GB in use).
Which Gpt Oss 46b quant should you choose?
Q4_K_M is the usual starting point for Gpt Oss 46b: it balances file size and quality well. Here it is a 34.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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
Source
Frequently asked questions about Gpt Oss 46b
How much VRAM does Gpt Oss 46b need?
About 35.4 GB at Q4_K_M with an 8K context window. That is the 34.5 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 Gpt Oss 46b on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gpt Oss 46b GGUF?
It depends on the quant: file is 0.0 GB, MXFP4_MOE is 25.8 GB, IQ1_M is 26.1 GB, IQ1_S is 26.1 GB, IQ2_XXS is 26.1 GB, IQ2_XS is 26.1 GB and 19 more.
What context length does Gpt Oss 46b support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download Gpt Oss 46b GGUF?
The files are on Hugging Face in the mradermacher/gpt-oss-46b-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 Gpt Oss 46b 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 Gpt Oss 46b on 8 GB VRAM?
Only the 0.04‑GB unknown quant can fit, but it may lack full functionality.
What is the memory requirement for the MXFP4_MOE quant?
It requires approximately 26.7‑GB of VRAM at an 8k context length.
Is the model licensed for commercial use?
Yes, it is released under the Apache‑2.0 license, which allows commercial deployment.