Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text generation

gpt-oss-20b-GGUF

by WINSTECHNET_AX axteam/gpt-oss-20b-GGUF

gpt-oss-20b-GGUF is an open-weight model for text generation from WINSTECHNET_AX, released under Apache License 2.0. Its published files total 13.8 GB.

GGUF build of openai/gpt-oss-20b for llama.cpp / Ollama / LM Studio. Converted by axteam with llama.cpp. The chat template (OpenAI harmony format) is embedded in the GGUF. Use a recent llama.cpp build (gpt-oss support, Aug-2025 or later).

Parameters—
Context—
Weights13.8 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By WINSTECHNET_AX, published under apache-2.0, revision ec0a2e9d8bdb.

GGUF build of openai/gpt-oss-20b for llama.cpp / Ollama / LM Studio. Converted by axteam with llama.cpp. The chat template (OpenAI harmony format) is embedded in the GGUF. Use a recent llama.cpp build (gpt-oss support, Aug-2025 or later). Reasoning effort can be set in the system prompt (Reasoning: low|medium|high). KV-cache type is a run-time choice in llama.cpp (not baked into the file): Apache-2.0, following the original openai/gpt-oss-20b. Weights, tokenizer, and chat template belong to OpenAI. This repo only re-packages them as GGUF. openai/gpt-oss-20b 의 GGUF 빌드 (llama.cpp·Ollama·LM Studio용). 변환: axteam (llama.cpp, chattemplate(OpenAI harmony)은 GGUF에 내장). - 파일…

Read WINSTECHNET_AX's full model card

gpt-oss-20b · GGUF (MXFP4)

GGUF build of openai/gpt-oss-20b for llama.cpp / Ollama / LM Studio. Converted by axteam with llama.cpp. The chat template (OpenAI harmony format) is embedded in the GGUF.

File Quant Size Notes
gpt-oss-20b-GGUF-MXFP4.gguf MXFP4 12.8 GB native 4-bit MoE weights (as released by OpenAI)

gpt-oss-20b is natively MXFP4 — the expert weights ship in 4-bit, so this single file is the faithful, full-quality build (no separate Q4/Q8 needed). It runs comfortably on a single 16 GB+ GPU, and easily on 48 GB. Architecture: gpt-oss · Mixture-of-Experts (~21B total, ~3.6B active). 128k context, adjustable reasoning effort.

Run with llama.cpp

Use a recent llama.cpp build (gpt-oss support, Aug-2025 or later).

# chat server (harmony template is embedded; --jinja uses it)
llama-server -m gpt-oss-20b-GGUF-MXFP4.gguf -c 8192 --jinja
# one-shot
llama-cli   -m gpt-oss-20b-GGUF-MXFP4.gguf --jinja -p "Explain MoE in one sentence."

Reasoning effort can be set in the system prompt (Reasoning: low|medium|high).

Reduce KV-cache memory (optional, run-time)

KV-cache type is a run-time choice in llama.cpp (not baked into the file):

llama-server -m gpt-oss-20b-GGUF-MXFP4.gguf -c 8192 --jinja \
  --cache-type-k q8_0 --cache-type-v q8_0 -fa on

Ollama

ollama run hf.co/axteam/gpt-oss-20b-GGUF

License

Apache-2.0, following the original openai/gpt-oss-20b. Weights, tokenizer, and chat template belong to OpenAI. This repo only re-packages them as GGUF.

한국어 요약

openai/gpt-oss-20b 의 GGUF 빌드 (llama.cpp·Ollama·LM Studio용). 변환: axteam (llama.cpp, chat_template(OpenAI harmony)은 GGUF에 내장).

  • 파일: gpt-oss-20b-GGUF-MXFP4.gguf (MXFP4, 12.8 GB) — gpt-oss는 원래부터 MXFP4(전문가 가중치가 4비트로 배포)라 이 한 파일이 곧 원본 품질. 별도 Q4/Q8 불필요. 16 GB급 GPU 1장에서도 동작, 48 GB면 여유.
  • 구조: gpt-oss · MoE(총 ~21B, 활성 ~3.6B), 128k 문맥, 추론 강도 조절 가능.
  • 실행: llama-server -m gpt-oss-20b-GGUF-MXFP4.gguf -c 8192 --jinja (harmony 템플릿 내장, --jinja로 사용)
  • KV 캐시 절감(런타임): --cache-type-k q8_0 --cache-type-v q8_0 -fa on (파일에 안 구움)
  • Ollama: ollama run hf.co/axteam/gpt-oss-20b-GGUF
  • 라이선스: 원본과 동일 Apache-2.0. 가중치·토크나이저·chat_template 권리는 OpenAI. 본 레포는 GGUF 재패키징만.

Identity and Version

Repository
axteam/gpt-oss-20b-GGUF
Publisher
WINSTECHNET_AX
Task
Text generation
Modality
Text
Library
llama.cpp
Parameters
Not stated by the source
Languages
gpt-oss
Revision
ec0a2e9d8bdb4a47d2a35d8009d76692e959a3ce
First published
2026-10-11
Last updated
2026-10-11

Files and Weights

3 files, 13.8 GB in total. The weights are 1 file totalling 13.8 GB in gguf.

Weights1 file · 13.8 GB
Documentation1 file · 2.9 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
gpt-oss-20b-GGUF-MXFP4.ggufWeights13.8 GB a9d6f3dba56e
README.mdDocumentation2.9 KB —
.gitattributesRepository1.6 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
13.8 GB
Download from WINSTECHNET_AX

Released by WINSTECHNET_AX through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published13.8 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About gpt-oss-20b-GGUF

Can I use gpt-oss-20b-GGUF commercially?

Yes. gpt-oss-20b-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers
View model

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers
View model

Model · Text generation

Ternary-Bonsai-2-27B-gguf

Prism ML

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at about 82% of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at 74.92…

Open weights apache-2.0 llama.cpp
View model

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers
View model

Fine-tune Qwen3 (14B) for free using our Google Colab notebook! - Read our Blog about Qwen3 support: unsloth.ai/blog/qwen3 - View the rest of our notebooks in our docs here. Qwen3-Coder is available in multiple sizes. Today, we're excited to introduce Qwen3-Coder-30B-A3B-Instruct. This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements: - Significant Performance among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks. - Long-context Capabilities with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale understanding. - Agentic Coding supporting for…

Open weights apache-2.0 transformers
View model

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp
View model