---
quantized_by: bobchenyx
base_model:
- openai/gpt-oss-20b
base_model_relation: quantized
tags:
- transformers
- GGUF
- llama.cpp
- gpt-oss
- openai
pipeline_tag: text-generation
license: apache-2.0
---

## Llamacpp Quantizations of gpt-oss-20b

Original model: Adopting **F16** from [unsloth/gpt-oss-20b-GGUF](https://huggingface.co/unsloth/gpt-oss-20b-GGUF).

MXFP4_MOE quant made with update in this PR [llama.cpp #15091](https://github.com/ggml-org/llama.cpp/pull/15091)

**MXFP4_MOE : 11.27 GiB (4.63 BPW)**

---
## Download(Example)

```
# !pip install huggingface_hub hf_transfer
import os
os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
from huggingface_hub import snapshot_download
snapshot_download(
    repo_id = "bobchenyx/gpt-oss-20b-GGUF",
    local_dir = "bobchenyx/gpt-oss-20b-GGUF",
    allow_patterns = ["*MXFP4_MOE*"],
)