decadence/ornith-1.5

decadence/ ornith-1.5

102 Downloads Updated 2 days ago

9B — GGUF — MLX — uncensored — sampling | ~5-11 GB

vision tools thinking

ollama run decadence/ornith-1.5:9b-base-abliterated-mlx-4bit

curl http://localhost:11434/api/chat \
  -d '{
    "model": "decadence/ornith-1.5:9b-base-abliterated-mlx-4bit",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='decadence/ornith-1.5:9b-base-abliterated-mlx-4bit',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'decadence/ornith-1.5:9b-base-abliterated-mlx-4bit',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model decadence/ornith-1.5:9b-base-abliterated-mlx-4bit

OpenCode

OpenCode ollama launch opencode --model decadence/ornith-1.5:9b-base-abliterated-mlx-4bit

Hermes Agent

Hermes Agent ollama launch hermes --model decadence/ornith-1.5:9b-base-abliterated-mlx-4bit

OpenClaw

OpenClaw ollama launch openclaw --model decadence/ornith-1.5:9b-base-abliterated-mlx-4bit

Models

Name

12 models

Size / Usage

Context

Input

ornith-1.5:9b-base-abliterated-mlx-4bit

5.1GB · 256K context window · Text · 2 days ago

ornith-1.5:9b-base-abliterated-mlx-4bit MLX

5.1GB

256K

Text

ornith-1.5:9b-base-abliterated-mlx-8bit

9.5GB · 256K context window · Text · 1 week ago

ornith-1.5:9b-base-abliterated-mlx-8bit MLX

9.5GB

256K

Text

ornith-1.5:9b-base-mlx-4bit

5.1GB · 256K context window · Text · 2 days ago

ornith-1.5:9b-base-mlx-4bit MLX

5.1GB

256K

Text

ornith-1.5:9b-base-mlx-8bit

9.5GB · 256K context window · Text · 1 week ago

ornith-1.5:9b-base-mlx-8bit MLX

9.5GB

256K

Text

ornith-1.5:9b-base-q4_k_m

6.7GB · 256K context window · Text, Image · 2 days ago

ornith-1.5:9b-base-q4_k_m

6.7GB

256K

Text, Image

ornith-1.5:9b-base-q8_0

11GB · 256K context window · Text, Image · 4 weeks ago

ornith-1.5:9b-base-q8_0

11GB

256K

Text, Image

ornith-1.5:9b-code-abliterated-mlx-4bit

5.1GB · 256K context window · Text · 2 days ago

ornith-1.5:9b-code-abliterated-mlx-4bit MLX

5.1GB

256K

Text

ornith-1.5:9b-code-abliterated-mlx-8bit

9.5GB · 256K context window · Text · 1 week ago

ornith-1.5:9b-code-abliterated-mlx-8bit MLX

9.5GB

256K

Text

ornith-1.5:9b-code-mlx-4bit

5.1GB · 256K context window · Text · 2 days ago

ornith-1.5:9b-code-mlx-4bit MLX

5.1GB

256K

Text

ornith-1.5:9b-code-mlx-8bit

9.5GB · 256K context window · Text · 1 week ago

ornith-1.5:9b-code-mlx-8bit MLX

9.5GB

256K

Text

ornith-1.5:9b-code-q4_k_m

6.7GB · 256K context window · Text, Image · 2 days ago

ornith-1.5:9b-code-q4_k_m

6.7GB

256K

Text, Image

ornith-1.5:9b-code-q8_0

11GB · 256K context window · Text, Image · 1 week ago

ornith-1.5:9b-code-q8_0

11GB

256K

Text, Image

Readme

Ornith 1.5 9B

model	type	quant	unc	size	source
ornith-1.5:9b-base-abliterated-mlx-4bit	MLX	int4	✓	5.1 GB	ressl
ornith-1.5:9b-base-abliterated-mlx-8bit	MLX	int8	✓	9.5 GB	ressl
ornith-1.5:9b-base-mlx-4bit	MLX	int4	-	5.1 GB	ornith-ai
ornith-1.5:9b-base-mlx-8bit	MLX	int8	-	9.5 GB	ornith-ai
ornith-1.5:9b-base-q4_k_m	GGUF	Q4_K_M	-	6.7 GB	ornith-ai
ornith-1.5:9b-base-q8_0	GGUF	Q8_0	-	10 GB	ornith-ai
ornith-1.5:9b-code-abliterated-mlx-4bit	MLX	int4	✓	5.1 GB	ressl
ornith-1.5:9b-code-abliterated-mlx-8bit	MLX	int8	✓	9.5 GB	ressl
ornith-1.5:9b-code-mlx-4bit	MLX	int4	-	5.1 GB	ornith-ai
ornith-1.5:9b-code-mlx-8bit	MLX	int8	-	9.5 GB	ornith-ai
ornith-1.5:9b-code-q4_k_m	GGUF	Q4_K_M	-	6.7 GB	ornith-ai
ornith-1.5:9b-code-q8_0	GGUF	Q8_0	-	10 GB	ornith-ai

Sampling Parameters

Following Ornith-1.5-9B Recommended sampling parameters:

parameter	base	code
temperature	1.0	0.6
top_p	0.95	0.95
top_k	20	20
min_p	0.0	0.0
presence_penalty	1.5	0.0
repetition_penalty	1.0	1.0

Vision

MLX version of Ornith-1.5-9B is stripped of vision. Non-MLX version has vision capability.

## Ornith 1.5 9B

model                               | type | quant | unc | size   | source
------------------------------------|------|-------|-----|--------|---
ornith-1.5:9b-base-abliterated-mlx-4bit | MLX  | int4  | ✓   | 5.1 GB | [ressl](https://huggingface.co/ressl/Ornith-1.5-9B-uncensored-MLX-4bit)
ornith-1.5:9b-base-abliterated-mlx-8bit | MLX  | int8  | ✓   | 9.5 GB | [ressl](https://huggingface.co/ressl/Ornith-1.5-9B-uncensored-MLX-8bit)
ornith-1.5:9b-base-mlx-4bit             | MLX  | int4  | -   | 5.1 GB | [ornith-ai](https://huggingface.co/ornith-ai/Ornith-1.5-9B-MLX-4bit)
ornith-1.5:9b-base-mlx-8bit             | MLX  | int8  | -   | 9.5 GB | [ornith-ai](https://huggingface.co/ornith-ai/Ornith-1.5-9B-MLX-8bit)
ornith-1.5:9b-base-q4_k_m               | GGUF | Q4_K_M | -   | 6.7 GB | [ornith-ai](https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF)
ornith-1.5:9b-base-q8_0                 | GGUF | Q8_0  | -   | 10 GB  | [ornith-ai](https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF)
ornith-1.5:9b-code-abliterated-mlx-4bit | MLX  | int4  | ✓   | 5.1 GB | [ressl](https://huggingface.co/ressl/Ornith-1.5-9B-uncensored-MLX-4bit)
ornith-1.5:9b-code-abliterated-mlx-8bit | MLX  | int8  | ✓   | 9.5 GB | [ressl](https://huggingface.co/ressl/Ornith-1.5-9B-uncensored-MLX-8bit)
ornith-1.5:9b-code-mlx-4bit             | MLX  | int4  | -   | 5.1 GB | [ornith-ai](https://huggingface.co/ornith-ai/Ornith-1.5-9B-MLX-4bit)
ornith-1.5:9b-code-mlx-8bit             | MLX  | int8  | -   | 9.5 GB | [ornith-ai](https://huggingface.co/ornith-ai/Ornith-1.5-9B-MLX-8bit)
ornith-1.5:9b-code-q4_k_m               | GGUF | Q4_K_M | -   | 6.7 GB | [ornith-ai](https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF)
ornith-1.5:9b-code-q8_0                 | GGUF | Q8_0  | -   | 10 GB  | [ornith-ai](https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF)

## Sampling Parameters

Following [Ornith-1.5-9B Recommended sampling parameters:](https://huggingface.co/ornith-ai/Ornith-1.5-9B#quickstart)

parameter          | base | code
-------------------|------|---
temperature        | 1.0  | 0.6
top_p              | 0.95 | 0.95
top_k              | 20   | 20
min_p              | 0.0  | 0.0
presence_penalty   | 1.5  | 0.0
repetition_penalty | 1.0  | 1.0

## Vision

MLX version of [Ornith-1.5-9B](https://huggingface.co/ornith-ai/Ornith-1.5-9B-MLX-8bit) is stripped of vision. Non-MLX version has vision capability.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)