mirror/LocalAI
1
0 Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-10-28 09:08:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

chore(gallery): add POCKET-Darwin-180B GGUF

Browse Source 
Add the published four-shard UD-Q4_K_XL build for llama.cpp with
revision-pinned downloads and verified SHA256 checksums. Document
installation, download size, text-only input, and sampling defaults.

Assisted-by: Codex:gpt-6

(cherry picked from commit e32d0f50de, mudler/LocalAI#12542)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
localai-org-maint-bot authored and Ettore Di Giacinto committed 2026-10-13 07:25:15 +00:00
1 parent 0dcedf061f
commit 36d5579ece
1 file changed
+51
Download Patch File Download Diff File Expand all files Collapse all files
gallery/index.yaml
+51
View File
@@ -1907,6 +1907,57 @@
- filename: llama-cpp/models/llm-jp-4-33b-thinking/llm-jp-4-33b-thinking-BF16.gguf
uri: huggingface://llm-jp/llm-jp-4-33b-thinking-gguf/llm-jp-4-33b-thinking-BF16.gguf
sha256: 7bb8465702b5c4a5d94e03e62921d5917181a2eda56da31edfdcd47fab2e9964
- name: pocket-darwin-180b-q4
url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls:
- https://huggingface.co/FINAL-Bench/Darwin-180B-RSI-R3
- https://huggingface.co/FINAL-Bench/POCKET-Darwin-180B-GGUF
description: |
POCKET-Darwin-180B is a text-only reasoning model based on
Qwen3.8-Flash-Next. This UD-Q4_K_XL GGUF build uses llama.cpp and
downloads all four shards (about 111.3 GB). It uses the embedded
chat template, an 8192-token default context, and the publisher's
recommended sampling settings. Weights use Qwen Community License 1.0.
license: other
tags:
- llm
- gguf
- cpu
- gpu
- qwen
- moe
- reasoning
overrides:
backend: llama-cpp
context_size: 8192
known_usecases:
- chat
options:
- use_jinja:true
parameters:
model: llama-cpp/models/pocket-darwin-180b/POCKET-Darwin-180B-UD-Q4_K_XL-00001-of-00004.gguf
temperature: 1
top_p: 0.95
top_k: 20
min_p: 0
repeat_penalty: 1
presence_penalty: 0
template:
use_tokenizer_template: true
files:
- filename: llama-cpp/models/pocket-darwin-180b/POCKET-Darwin-180B-UD-Q4_K_XL-00001-of-00004.gguf
sha256: 8dd7789f02ff62e07f3a4dbd546d21fa6dc45cdbaac367631571d80cac8206a5
uri: https://huggingface.co/FINAL-Bench/POCKET-Darwin-180B-GGUF/resolve/71f3b4d3a68af20812af27b2e611501ab43baf1e/POCKET-Darwin-180B-UD-Q4_K_XL-00001-of-00004.gguf
- filename: llama-cpp/models/pocket-darwin-180b/POCKET-Darwin-180B-UD-Q4_K_XL-00002-of-00004.gguf
sha256: 8d2a48cace8791b2655173f8b507eb985471834511908006da6b4166b2155794
uri: https://huggingface.co/FINAL-Bench/POCKET-Darwin-180B-GGUF/resolve/71f3b4d3a68af20812af27b2e611501ab43baf1e/POCKET-Darwin-180B-UD-Q4_K_XL-00002-of-00004.gguf
- filename: llama-cpp/models/pocket-darwin-180b/POCKET-Darwin-180B-UD-Q4_K_XL-00003-of-00004.gguf
sha256: 0adc56c67b89cbfcaa67780e78fc0a15666ef2a1ebf5cdc51611fc1198ae256f
uri: https://huggingface.co/FINAL-Bench/POCKET-Darwin-180B-GGUF/resolve/71f3b4d3a68af20812af27b2e611501ab43baf1e/POCKET-Darwin-180B-UD-Q4_K_XL-00003-of-00004.gguf
- filename: llama-cpp/models/pocket-darwin-180b/POCKET-Darwin-180B-UD-Q4_K_XL-00004-of-00004.gguf
sha256: 0f45b1445b2a4d032d44766936107031d2f503b6bc7eb7fcf80f35232477ab5b
uri: https://huggingface.co/FINAL-Bench/POCKET-Darwin-180B-GGUF/resolve/71f3b4d3a68af20812af27b2e611501ab43baf1e/POCKET-Darwin-180B-UD-Q4_K_XL-00004-of-00004.gguf
- name: huihui-qwen3.8-flash-next-abliterated-q4
url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls: