Gpt-Oss-120B needs about 63.9 GB of memory at Q4_K_M (a 62.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 16 quants, from 62.6 GB (Q3_K_S) to 65.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
120‑billion‑parameter GPT‑OSS model for high‑reasoning tasks
Gpt‑Oss‑120B is a 120 billion‑parameter GPT‑OSS model. It is trained on a 131 072‑token context and released under Apache 2.0. The model is available in multiple GGUF quantizations for local inference.
Good at
- High‑reasoning and agentic tasks
- Chain‑of‑thought generation
- Fine‑tuning for custom workloads
Limits
- Requires large GPU memory (≈64 GB for 8 k context)
- No vision or audio support
- Must use harmony response format
Best for
- Enterprise reasoning pipelines
- Custom agent development
- Fine‑tuning research projects
Who it’s for. Developers and researchers needing a large, open‑weight model for reasoning and agentic applications. The model is suitable for production use on high‑end GPUs and for experimentation under an Apache 2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 62.6 GB (2 parts) | 63.7 GB | Too big | Get file → | |
| Q2_K | 62.6 GB (2 parts) | 63.7 GB | Too big | Get file → | |
| Q4_0 | 62.6 GB (2 parts) | 63.7 GB | Too big | Get file → | |
| Q3_K_M | 62.6 GB (2 parts) | 63.7 GB | Too big | Get file → | |
| Q4_1 | 62.7 GB (2 parts) | 63.8 GB | Too big | Get file → | |
| Q4_K_S | 62.8 GB (2 parts) | 63.9 GB | Too big | Get file → | |
| Q4_K_M | 62.8 GB (2 parts) | 63.9 GB | Too big | Get file → | |
| Q2_K_L | 62.9 GB (2 parts) | 64.0 GB | Too big | Get file → | |
| Q5_K_S | 62.9 GB (2 parts) | 64.0 GB | Too big | Get file → | |
| Q5_K_M | 62.9 GB (2 parts) | 64.0 GB | Too big | Get file → | |
| Q4_K_XL | 63.0 GB (2 parts) | 64.1 GB | Too big | Get file → | |
| Q6_K | 63.3 GB (2 parts) | 64.4 GB | Too big | Get file → | |
| Q6_K_XL | 63.3 GB (2 parts) | 64.4 GB | Too big | Get file → | |
| Q8_0 | 63.4 GB (2 parts) | 64.5 GB | Too big | Get file → | |
| Q8_K_XL | 64.5 GB (2 parts) | 65.6 GB | Too big | Get file → | |
| F16 | 65.4 GB | 66.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_1 (≈63 GB memory). For 16 GB VRAM, Q4_K_S or Q4_K_M are suitable. For 80 GB VRAM, Q8_0 or Q8_K_XL provide the best precision. Memory estimates are approximate.
What GPU do you need for Gpt-Oss-120B?
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: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Gpt-Oss-120B quant should you choose?
Q4_K_M is the usual starting point for Gpt-Oss-120B: it balances file size and quality well. Here it is a 62.8 GB file.
The Q8_0 file is 63.4 GB, about 1.0 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 Q3_K_S at 62.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gpt-Oss-120B
How much VRAM does Gpt-Oss-120B need?
About 63.9 GB at Q4_K_M with an 8K context window. That is the 62.8 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-120B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 63.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gpt-Oss-120B GGUF?
It depends on the quant: Q3_K_S is 62.6 GB, Q2_K is 62.6 GB, Q4_0 is 62.6 GB, Q3_K_M is 62.6 GB, Q4_1 is 62.7 GB, Q4_K_S is 62.8 GB and 10 more.
What context length does Gpt-Oss-120B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.
Where can I download Gpt-Oss-120B GGUF?
The files are on Hugging Face in the unsloth/gpt-oss-120b-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-120B 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.
Does the model support vision or audio?
No, the model only handles text input and output.
What license applies to this model?
The model is released under the Apache 2.0 license, allowing free use and modification.