mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-28 09:05:05 -04:00
Merge PR #12293: chore(gallery): add Swift 1.5 GSQ-RCO variants
Signed-off-by: Ettore Di Giacinto <mudler@localai.io> # Conflicts: # docs/content/features/model-gallery.md
This commit is contained in:
Ettore Di Giacinto committed
commit
4693ccf737
2 files changed
+187
No files matched your search
@@ -65,6 +65,21 @@ The files use standard llama.cpp quantization types and the Apache-2.0 license.
|
||||
See the [publisher's model card](https://huggingface.co/agentionai/Qwen3.8-27B-AP-GGUF)
|
||||
for quantization details. These entries do not enable MTP speculative decoding.
|
||||
|
||||
## Swift 1.5 Qwen3.8-27B GSQ-RCO
|
||||
|
||||
Install `swift-1.5-qwen3.8-27b-gsq-rco` for text chat with llama.cpp.
|
||||
The gallery groups IQ2_XS, IQ2_S, IQ3_XXS, and IQ3_S quantizations of this 27B reasoning and coding model.
|
||||
To select IQ3_S explicitly, run:
|
||||
|
||||
```bash
|
||||
local-ai models install swift-1.5-qwen3.8-27b-gsq-rco --variant swift-1.5-qwen3.8-27b-gsq-rco-iq3-s
|
||||
```
|
||||
|
||||
The configurations use the embedded chat template and default to 32,768 context tokens.
|
||||
These builds support text chat only: the publisher has no verified vision projector for this release.
|
||||
They use standard GGUF files without MTP decoding.
|
||||
See the [model card](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF) and [Swift Open License v1.0](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/blob/main/LICENSE) for usage terms.
|
||||
|
||||
## MiMo-V2.6-Distill-Qwen-9B
|
||||
|
||||
Install `mimo-v2.6-distill-qwen-9b` for text and image chat with llama.cpp.
|
||||
|
||||
@@ -6017,6 +6017,178 @@
|
||||
- filename: llama-cpp/mmproj/qwen3.8-27b-ridge/mmproj-Qwen3.8-27B-BF16.gguf
|
||||
uri: huggingface://empero-ai/Qwen3.8-27B-Ridge-GGUF/mmproj-Qwen3.8-27B-BF16.gguf
|
||||
sha256: 52228402ce4823f10705d901813cd43ced71859524cf2d8bf83305ad6b7dcbc2
|
||||
- name: "swift-1.5-qwen3.8-27b-gsq-rco"
|
||||
variants:
|
||||
- model: swift-1.5-qwen3.8-27b-gsq-rco-iq2-s
|
||||
- model: swift-1.5-qwen3.8-27b-gsq-rco-iq3-xxs
|
||||
- model: swift-1.5-qwen3.8-27b-gsq-rco-iq3-s
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
urls:
|
||||
- https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b
|
||||
- https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF
|
||||
license: "swift-open-license-1.0"
|
||||
description: |
|
||||
Swift 1.5 is a 27B Qwen3.8 fine-tune for reasoning, coding, and agent tasks.
|
||||
This IQ2_XS GGUF uses GSQ-RCO mixed-precision quantization with llama.cpp.
|
||||
Text chat only; the publisher provides no verified vision projector for this release.
|
||||
The weights use the Swift Open License v1.0.
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- reasoning
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
min_p: 0
|
||||
model: llama-cpp/models/swift-1.5-qwen3.8-27b-gsq-rco/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_XS.gguf
|
||||
presence_penalty: 0
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: 20
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/swift-1.5-qwen3.8-27b-gsq-rco/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_XS.gguf
|
||||
sha256: 714c509c3fc496ea4abc409097658df7cd218bc966f78e1459fc1649758a9de8
|
||||
uri: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/resolve/d74895bbe5db4bec1e0024e7cc87d59c02d7631a/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_XS.gguf
|
||||
- name: "swift-1.5-qwen3.8-27b-gsq-rco-iq2-s"
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
urls:
|
||||
- https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b
|
||||
- https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF
|
||||
license: "swift-open-license-1.0"
|
||||
description: |
|
||||
Swift 1.5 is a 27B Qwen3.8 fine-tune for reasoning, coding, and agent tasks.
|
||||
This IQ2_S GGUF uses GSQ-RCO mixed-precision quantization with llama.cpp.
|
||||
Text chat only; the publisher provides no verified vision projector for this release.
|
||||
The weights use the Swift Open License v1.0.
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- reasoning
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
min_p: 0
|
||||
model: llama-cpp/models/swift-1.5-qwen3.8-27b-gsq-rco/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S.gguf
|
||||
presence_penalty: 0
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: 20
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/swift-1.5-qwen3.8-27b-gsq-rco/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S.gguf
|
||||
sha256: 08fac9876117b2cadb6b79fc7708d9612511c2fa31f3726f162e757870272455
|
||||
uri: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/resolve/d74895bbe5db4bec1e0024e7cc87d59c02d7631a/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ2_S.gguf
|
||||
- name: "swift-1.5-qwen3.8-27b-gsq-rco-iq3-xxs"
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
urls:
|
||||
- https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b
|
||||
- https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF
|
||||
license: "swift-open-license-1.0"
|
||||
description: |
|
||||
Swift 1.5 is a 27B Qwen3.8 fine-tune for reasoning, coding, and agent tasks.
|
||||
This IQ3_XXS GGUF uses GSQ-RCO mixed-precision quantization with llama.cpp.
|
||||
Text chat only; the publisher provides no verified vision projector for this release.
|
||||
The weights use the Swift Open License v1.0.
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- reasoning
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
min_p: 0
|
||||
model: llama-cpp/models/swift-1.5-qwen3.8-27b-gsq-rco/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS.gguf
|
||||
presence_penalty: 0
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: 20
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/swift-1.5-qwen3.8-27b-gsq-rco/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS.gguf
|
||||
sha256: 86969b8bde72e602bfb42deb83eb8bb3706c8f14250641f6444dd2355f934ac2
|
||||
uri: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/resolve/d74895bbe5db4bec1e0024e7cc87d59c02d7631a/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS.gguf
|
||||
- name: "swift-1.5-qwen3.8-27b-gsq-rco-iq3-s"
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
urls:
|
||||
- https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b
|
||||
- https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF
|
||||
license: "swift-open-license-1.0"
|
||||
description: |
|
||||
Swift 1.5 is a 27B Qwen3.8 fine-tune for reasoning, coding, and agent tasks.
|
||||
This IQ3_S GGUF uses GSQ-RCO mixed-precision quantization with llama.cpp.
|
||||
Text chat only; the publisher provides no verified vision projector for this release.
|
||||
The weights use the Swift Open License v1.0.
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- reasoning
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
min_p: 0
|
||||
model: llama-cpp/models/swift-1.5-qwen3.8-27b-gsq-rco/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S.gguf
|
||||
presence_penalty: 0
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: 20
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/swift-1.5-qwen3.8-27b-gsq-rco/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S.gguf
|
||||
sha256: 1333c6ea70ef348d4ac6d62732772e8ad6571ac5b3754c14ed54f1a0d904a786
|
||||
uri: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF/resolve/d74895bbe5db4bec1e0024e7cc87d59c02d7631a/Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S.gguf
|
||||
- !!merge <<: *qwen3-8-27b
|
||||
name: "qwen3.8-27b-gsq-rco-iq2-xs"
|
||||
variants: []
|
||||
|
||||
Reference in new issue
Block a user