feat(gallery): add Tiel MTP quantization variants

Offer Q5, Q6, and Q8 MTP builds through the existing Tiel entry.
Pin weights and the vision projector to verified HF artifacts.
Document how to select a build explicitly.

Assisted-by: Codex:GPT-6
This commit is contained in:
localai-org-maint-bot committed 2026-09-09 08:05:42 +00:00
1 parent dc353aecb6
commit 73f1b7a954
2 files changed
+163

No files matched your search

+7
View File
@@ -233,6 +233,13 @@ whole page has variants.
curl http://localhost:8080/api/models | jq '.models[] | select(.has_variants) | .name'
```
The Tiel-Coder gallery entry offers Q4, Q5, Q6, and Q8 MTP builds for
llama.cpp, each with the BF16 vision projector. To select the Q6 MTP build:
```bash
local-ai models install tiel-coder-35b-a3b-q4 --variant tiel-coder-35b-a3b-q6-mtp
```
### Collapsing the listing to one row per model
By default the listing returns every entry, including the individual builds a
+156
View File
@@ -2415,6 +2415,9 @@
name: "tiel-coder-35b-a3b-q4"
variants:
- model: tiel-coder-35b-a3b-q4-mtp
- model: tiel-coder-35b-a3b-q5-mtp
- model: tiel-coder-35b-a3b-q6-mtp
- model: tiel-coder-35b-a3b-q8-mtp
- model: tiel-coder-35b-a3b-q8
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
@@ -2515,6 +2518,159 @@
- filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf
uri: huggingface://peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/mmproj-BF16.gguf
sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837
- !!merge <<: *tiel-coder-35b-a3b
name: "tiel-coder-35b-a3b-q5-mtp"
variants: []
last_checked: "2026-09-09"
urls:
- https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B
- https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP
description: |
Tiel-Coder-35B-A3B in Q5_K_XL format with MTP speculative decoding and a
BF16 vision projector.
tags:
- llm
- gguf
- cpu
- gpu
- qwen
- moe
- reasoning
- thinking
- coding
- agent
- tools
- vision
- multimodal
- long-context
- mtp
overrides:
backend: llama-cpp
context_size: 262144
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
- vision
mmproj: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf
options:
- use_jinja:true
- spec_type:draft-mtp
parameters:
model: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL.gguf
template:
use_tokenizer_template: true
files:
- filename: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL.gguf
uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL.gguf
sha256: 83278fd1ea9923edb45cf6d373a8aa6475fb1f855795e085b9e6252bc53f24fa
- filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf
uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/mmproj-BF16.gguf
sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837
- !!merge <<: *tiel-coder-35b-a3b
name: "tiel-coder-35b-a3b-q6-mtp"
variants: []
last_checked: "2026-09-09"
urls:
- https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B
- https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP
description: |
Tiel-Coder-35B-A3B in Q6_K_XL format with MTP speculative decoding and a
BF16 vision projector.
tags:
- llm
- gguf
- cpu
- gpu
- qwen
- moe
- reasoning
- thinking
- coding
- agent
- tools
- vision
- multimodal
- long-context
- mtp
overrides:
backend: llama-cpp
context_size: 262144
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
- vision
mmproj: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf
options:
- use_jinja:true
- spec_type:draft-mtp
parameters:
model: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf
template:
use_tokenizer_template: true
files:
- filename: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf
uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf
sha256: a13a71ecfd00779fa3e0071674da61afbdffd42050f22173f4142989975573ba
- filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf
uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/mmproj-BF16.gguf
sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837
- !!merge <<: *tiel-coder-35b-a3b
name: "tiel-coder-35b-a3b-q8-mtp"
variants: []
last_checked: "2026-09-09"
urls:
- https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B
- https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP
description: |
Tiel-Coder-35B-A3B in Q8_K_XL format with MTP speculative decoding and a
BF16 vision projector.
tags:
- llm
- gguf
- cpu
- gpu
- qwen
- moe
- reasoning
- thinking
- coding
- agent
- tools
- vision
- multimodal
- long-context
- mtp
overrides:
backend: llama-cpp
context_size: 262144
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
- vision
mmproj: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf
options:
- use_jinja:true
- spec_type:draft-mtp
parameters:
model: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf
template:
use_tokenizer_template: true
files:
- filename: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf
uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf
sha256: 8384abe448e6159b1d43249be9c51f68fe5771e962bb39e3ee89ad1215385310
- filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf
uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/mmproj-BF16.gguf
sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837
- !!merge <<: *tiel-coder-35b-a3b
name: "tiel-coder-35b-a3b-q8"
variants: []