mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-30 09:57:57 -04:00
gallery: add Laguna XS 2.1 GGUF variants (#11202)
Add the official Q4_K_M build and seven APEX quality and size variants for llama.cpp. Assisted-by: Codex:gpt-5 [Hugging Face API] Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
This commit is contained in:
localai-org-maint-bot
committed by
GitHub
GitHub
parent
4b917936ef
commit
c5a7d394a5
@@ -1140,6 +1140,238 @@
|
||||
- filename: llama-cpp/models/Gemmable-4-12B-MTP-GGUF/gemmable-4-12b-Q4_K_M-mtp.gguf
|
||||
sha256: 217dc0ed177ecc733f801a851c3e3854cf1b17a1f86cd5430c0a7f82d93027bc
|
||||
uri: https://huggingface.co/Mia-AiLab/Gemmable-4-12B-MTP-GGUF/resolve/main/gemmable-4-12b-Q4_K_M-mtp.gguf
|
||||
- &laguna-xs-2-1
|
||||
name: "laguna-xs-2.1"
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
variants:
|
||||
- model: laguna-xs-2.1-apex-i-quality
|
||||
- model: laguna-xs-2.1-apex-i-balanced
|
||||
- model: laguna-xs-2.1-apex-i-compact
|
||||
- model: laguna-xs-2.1-apex-i-mini
|
||||
- model: laguna-xs-2.1-apex-quality
|
||||
- model: laguna-xs-2.1-apex-balanced
|
||||
- model: laguna-xs-2.1-apex-compact
|
||||
urls:
|
||||
- https://huggingface.co/poolside/Laguna-XS-2.1
|
||||
- https://huggingface.co/poolside/Laguna-XS-2.1-GGUF
|
||||
- https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF
|
||||
description: |
|
||||
Laguna XS 2.1 is Poolside's 33B-parameter, 3B-active Mixture-of-Experts model for agentic coding and long-horizon work on local machines. It supports tool use, interleaved reasoning, and a native 262K-token context window. This default entry uses the official 20.3 GB Q4_K_M GGUF.
|
||||
|
||||
License: OpenMDW 1.1.
|
||||
license: "other"
|
||||
icon: https://poolside.ai/assets/laguna/laguna-xs2-1-banner.svg
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- moe
|
||||
- reasoning
|
||||
- code
|
||||
- agent
|
||||
- tools
|
||||
- long-context
|
||||
last_checked: "2026-07-30"
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
- completion
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: llama-cpp/models/poolside/Laguna-XS-2.1-GGUF/Laguna-XS-2.1-Q4_K_M.gguf
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/poolside/Laguna-XS-2.1-GGUF/Laguna-XS-2.1-Q4_K_M.gguf
|
||||
sha256: 1ac7079101fca5a6df8c5a7523a3c30ea7d1c0e4b1258090e7d6d4039287f6cb
|
||||
uri: https://huggingface.co/poolside/Laguna-XS-2.1-GGUF/resolve/main/Laguna-XS-2.1-Q4_K_M.gguf
|
||||
- !!merge <<: *laguna-xs-2-1
|
||||
name: "laguna-xs-2.1-apex-i-quality"
|
||||
variants: []
|
||||
description: |
|
||||
Laguna XS 2.1 in the 21.8 GB APEX-I Quality format. This is the highest-fidelity importance-matrix APEX build for llama.cpp.
|
||||
|
||||
License: OpenMDW 1.1.
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
- completion
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-I-Quality.gguf
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-I-Quality.gguf
|
||||
sha256: e15e4b9c7c5833c9a58bc70c9745f0cd21e00d4f9edd0c114cd39862ebe545c3
|
||||
uri: https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF/resolve/main/Laguna-XS-2.1-APEX-I-Quality.gguf
|
||||
- !!merge <<: *laguna-xs-2-1
|
||||
name: "laguna-xs-2.1-apex-i-balanced"
|
||||
variants: []
|
||||
description: |
|
||||
Laguna XS 2.1 in the 24.3 GB APEX-I Balanced format, an importance-matrix build balancing fidelity and memory use for llama.cpp.
|
||||
|
||||
License: OpenMDW 1.1.
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
- completion
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-I-Balanced.gguf
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-I-Balanced.gguf
|
||||
sha256: 64f0a1aab7a72121e68f7c2f6814471f0bd4a87130e5d0d8dff3003eb74b5510
|
||||
uri: https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF/resolve/main/Laguna-XS-2.1-APEX-I-Balanced.gguf
|
||||
- !!merge <<: *laguna-xs-2-1
|
||||
name: "laguna-xs-2.1-apex-i-compact"
|
||||
variants: []
|
||||
description: |
|
||||
Laguna XS 2.1 in the 15.8 GB APEX-I Compact format, an importance-matrix build tuned for lower memory use in llama.cpp.
|
||||
|
||||
License: OpenMDW 1.1.
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
- completion
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-I-Compact.gguf
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-I-Compact.gguf
|
||||
sha256: b674541db815d8829e4c57bd56cffebbd49e9822e284e69f199ae7fbd0b705d2
|
||||
uri: https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF/resolve/main/Laguna-XS-2.1-APEX-I-Compact.gguf
|
||||
- !!merge <<: *laguna-xs-2-1
|
||||
name: "laguna-xs-2.1-apex-i-mini"
|
||||
variants: []
|
||||
description: |
|
||||
Laguna XS 2.1 in the 12.8 GB APEX-I Mini format, the smallest importance-matrix APEX build for llama.cpp.
|
||||
|
||||
License: OpenMDW 1.1.
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
- completion
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-I-Mini.gguf
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-I-Mini.gguf
|
||||
sha256: 04d7ccf014da825f20d2d09e996258faf399f3f2176d57fd7ce375b8b8d71de1
|
||||
uri: https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF/resolve/main/Laguna-XS-2.1-APEX-I-Mini.gguf
|
||||
- !!merge <<: *laguna-xs-2-1
|
||||
name: "laguna-xs-2.1-apex-quality"
|
||||
variants: []
|
||||
description: |
|
||||
Laguna XS 2.1 in the 21.8 GB APEX Quality format, the highest-fidelity non-imatrix APEX build for llama.cpp.
|
||||
|
||||
License: OpenMDW 1.1.
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
- completion
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-Quality.gguf
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-Quality.gguf
|
||||
sha256: fd7dba637bcb1c3e1590a9b33c40bd5fe411a1156f6520b14ccd6dfb344feffd
|
||||
uri: https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF/resolve/main/Laguna-XS-2.1-APEX-Quality.gguf
|
||||
- !!merge <<: *laguna-xs-2-1
|
||||
name: "laguna-xs-2.1-apex-balanced"
|
||||
variants: []
|
||||
description: |
|
||||
Laguna XS 2.1 in the 24.3 GB APEX Balanced format, balancing fidelity and memory use for llama.cpp.
|
||||
|
||||
License: OpenMDW 1.1.
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
- completion
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-Balanced.gguf
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-Balanced.gguf
|
||||
sha256: 997c6b9de70c594423f21cef07f3ad45944bbbe37a0ee10b4ea20bf094e615fa
|
||||
uri: https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF/resolve/main/Laguna-XS-2.1-APEX-Balanced.gguf
|
||||
- !!merge <<: *laguna-xs-2-1
|
||||
name: "laguna-xs-2.1-apex-compact"
|
||||
variants: []
|
||||
description: |
|
||||
Laguna XS 2.1 in the 15.8 GB APEX Compact format, tuned for lower memory use in llama.cpp.
|
||||
|
||||
License: OpenMDW 1.1.
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
- completion
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-Compact.gguf
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/mudler/Laguna-XS-2.1-APEX-GGUF/Laguna-XS-2.1-APEX-Compact.gguf
|
||||
sha256: cb2604e56eec8037e553cc91a81b454a816695d8443a18a162856fb6d1c8128a
|
||||
uri: https://huggingface.co/mudler/Laguna-XS-2.1-APEX-GGUF/resolve/main/Laguna-XS-2.1-APEX-Compact.gguf
|
||||
- &laguna-s-2-1-q8
|
||||
name: "laguna-s-2.1-q8"
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
|
||||
Reference in New Issue
Block a user