Model Intelligence Sheet
1bit-MONSTER/gpt-oss-120b-GGUF overview
gpt oss 120b — GGUF UD Q4 K XL Unsloth's Dynamic 2.0 UD Q4 K XL GGUF for OpenAI's gpt oss 120b a ~117B MoE , re hosted for the 1bit engine https://github.com/1…
Runs locally from ~12.25 GB disk (16 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | 1bit-MONSTER/gpt-oss-120b-GGUF |
|---|---|
| Author | 1bit-MONSTER |
| Pipeline | — |
| License | apache-2.0 |
| Base model | openai/gpt-oss-120b,unsloth/gpt-oss-120b-GGUF |
| Last modified | 2026-09-26T16:40:05.000Z |
Model README
---
license: apache-2.0
base_model:
- openai/gpt-oss-120b
- unsloth/gpt-oss-120b-GGUF
tags:
- gguf
- moe
---
gpt-oss-120b — GGUF (UD-Q4_K_XL)
Unsloth's Dynamic 2.0 UD-Q4_K_XL GGUF for OpenAI's gpt-oss-120b (a ~117B MoE), re-hosted
for the 1bit engine.
Contents
UD-Q4_K_XL/gpt-oss-120b-UD-Q4_K_XL-00001-of-00002.ggufUD-Q4_K_XL/gpt-oss-120b-UD-Q4_K_XL-00002-of-00002.gguf
~63 GiB total. Needs a comparable amount of resident memory to run.
Running it
Point at the first shard — llama.cpp finds the rest automatically:
1bit serve -m UD-Q4_K_XL/gpt-oss-120b-UD-Q4_K_XL-00001-of-00002.gguf --device vulkanAttribution
- Base model: openai/gpt-oss-120b, Apache 2.0.
- Quantization: unsloth/gpt-oss-120b-GGUF.
- License: Apache 2.0, inherited from the base model.
Run 1bit-MONSTER/gpt-oss-120b-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models