Skip to content

chore(model gallery): 🤖 add 1 new models via gallery agent #10439

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mudler merged 1 commit into from
Jun 22, 2026
+92 −0
Merged

chore(model gallery): 🤖 add 1 new models via gallery agent #10439

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
92 changes: 92 additions & 0 deletions gallery/index.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,96 @@
---
- name: "glm-5.2"
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
- https://huggingface.co/unsloth/GLM-5.2-GGUF
description: |
# GLM-5.2

👋 Join our WeChat or Discord community.

📖 Check out the GLM-5.2 blog and GLM-5 Technical report.

📍 Use GLM-5.2 API services on Z.ai API Platform.

🔜 Try GLM-5.2 here.

[Paper]
[GitHub]

## Introduction

We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a **solid 1M-token context**. GLM-5.2's new capabilities include:
- **Solid 1M Context:** A solid 1M-token context that stably sustains long-horizon work
- **Advanced Coding with Flexible Effort**: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency
- **Improved Architecture**: We propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9× at a 1M context length. We also improve GLM-5.2’s MTP layer for speculative decoding, increasing the acceptance length by up to 20%
- **Pure Open**: An MIT open-source license — no regional limits, technical access without borders

## Benchmark

## Serve GLM-5.2 Locally

...
license: "mit"
tags:
- llm
- gguf
icon: https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/bench_52.png
overrides:
backend: llama-cpp
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
options:
- use_jinja:true
- spec_type:draft-mtp
- spec_n_max:6
- spec_p_min:0.75
parameters:
min_p: 0.01
model: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00001-of-00011.gguf
repeat_penalty: 1
temperature: 1
top_k: -1
top_p: 0.95
template:
use_tokenizer_template: true
files:
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00001-of-00011.gguf
sha256: 3256ac8c290273f0965ff39e93a8bcd07dc99bcd23e923bd4b7306ef39061038
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00001-of-00011.gguf
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00002-of-00011.gguf
sha256: 1020105e78d862988a6cabb3a78eafa75f29666ab8a5fd10de1b9b8c8a6bc5e8
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00002-of-00011.gguf
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00003-of-00011.gguf
sha256: 0b36f406e120759290894ea4960d5086f9b362a8c8f9c7fcaad24b4471172efb
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00003-of-00011.gguf
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00004-of-00011.gguf
sha256: 04b19199f52ba29e7f9966b15df3fbc2d1e5c56cd6343c405076be7174d49d32
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00004-of-00011.gguf
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00005-of-00011.gguf
sha256: 5cb76d724ee16e80c1cb6aba29aacd76161e7a6f147079be3447501c06d95f2c
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00005-of-00011.gguf
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00006-of-00011.gguf
sha256: ec2c65255c834b686f066e350bc5b8d8a7020cd1133f0ee9e819d2fb5d3afad0
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00006-of-00011.gguf
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00007-of-00011.gguf
sha256: 53c8328852ca0b6791a9a9243bcc56157305adca8526a646054389845e7445a9
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00007-of-00011.gguf
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00008-of-00011.gguf
sha256: 9a23bfb21c5f6fcc94b0329c108ec1ef3fdbd815c57eeb0bf105d26861d7271e
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00008-of-00011.gguf
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00009-of-00011.gguf
sha256: 71088054fb1a09a4f38e2ee8a726526790660a4f77ead817f75cb7a484bdb0b8
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00009-of-00011.gguf
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00010-of-00011.gguf
sha256: 848db99658faf24971df23638281305a15bdc187cbcaed968952ed9e9c835b50
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00010-of-00011.gguf
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00011-of-00011.gguf
sha256: 629e23bce250fb500d9a190de7249c2882af524aacc112ce507a871ed5bebf90
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00011-of-00011.gguf
- name: "qwen3.6-35b-a3b-nvfp4-mtp"
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
Expand Down
Loading