Hugging Face's logo

Spaces:
GestaltLabs
/
README
Running

App Files Community
DJLougen commited on
Commit
8157ad7
·
verified ·
1 Parent(s): 3297dc6

Add Ornstein-Hermes-3.6-27b + 35B-A3B MLX builds; restructure Ornstein section

Browse files
Files changed (1) hide show
  1. README.md +14 -5
README.md CHANGED
@@ -31,12 +31,21 @@ GestaltLabs is the research home for the **Ornstein**, **Harmonic**, **CHIMERA**
31
  ## Featured Model Lines
32
 
33
  ### Ornstein
34
- Multimodal reasoning line across 27B–35B scales with strong local deployment characteristics.
35
 
36
- - [GestaltLabs/Ornstein-3.6-27B](https://huggingface.co/GestaltLabs/Ornstein-3.6-27B)
37
- - [GestaltLabs/Ornstein-3.6-27B-GGUF](https://huggingface.co/GestaltLabs/Ornstein-3.6-27B-GGUF)
38
- - [DJLougen/Ornstein3.6-35B-A3B-GGUF](https://huggingface.co/DJLougen/Ornstein3.6-35B-A3B-GGUF)
39
- - [DJLougen/Ornstein-27B-v2-GGUF](https://huggingface.co/DJLougen/Ornstein-27B-v2-GGUF)
 
 
 
 
 
 
 
 
 
40
 
41
  ### CHIMERA
42
  *Coming soon* — reasoning-focused models with explicit self-correction and agent trace supervision.
 
31
  ## Featured Model Lines
32
 
33
  ### Ornstein
34
+ Multimodal and MoE reasoning line across 27B–35B scales, shipped in formats for every common local-inference stack.
35
 
36
+ **Ornstein-3.6-27B** — multimodal base (Qwen 3.6 27B)
37
+ - [Base](https://huggingface.co/GestaltLabs/Ornstein-3.6-27B) · [GGUF](https://huggingface.co/GestaltLabs/Ornstein-3.6-27B-GGUF)
38
+
39
+ **Ornstein-Hermes-3.6-27b** — Hermes-format function-calling fine-tune (multimodal, tool-use)
40
+ - [Base](https://huggingface.co/GestaltLabs/Ornstein-Hermes-3.6-27b) · [GGUF](https://huggingface.co/GestaltLabs/Ornstein-Hermes-3.6-27b-GGUF)
41
+ - MLX: [bf16](https://huggingface.co/GestaltLabs/Ornstein-Hermes-3.6-27b-MLX-16bit) · [8-bit](https://huggingface.co/GestaltLabs/Ornstein-Hermes-3.6-27b-MLX-8bit) · [6-bit](https://huggingface.co/GestaltLabs/Ornstein-Hermes-3.6-27b-MLX-6bit) · [4-bit](https://huggingface.co/GestaltLabs/Ornstein-Hermes-3.6-27b-MLX-4bit)
42
+
43
+ **Ornstein3.6-35B-A3B** — text-only Mixture-of-Experts (34.7B total, ~3B active)
44
+ - [Base](https://huggingface.co/DJLougen/Ornstein3.6-35B-A3B) · [GGUF](https://huggingface.co/DJLougen/Ornstein3.6-35B-A3B-GGUF)
45
+ - MLX: [bf16](https://huggingface.co/DJLougen/Ornstein3.6-35B-A3B-MLX-16bit) · [8-bit](https://huggingface.co/DJLougen/Ornstein3.6-35B-A3B-MLX-8bit) · [6-bit](https://huggingface.co/DJLougen/Ornstein3.6-35B-A3B-MLX-6bit) · [4-bit](https://huggingface.co/DJLougen/Ornstein3.6-35B-A3B-MLX-4bit)
46
+
47
+ **Ornstein-27B-v2** — earlier 27B revision
48
+ - [GGUF](https://huggingface.co/DJLougen/Ornstein-27B-v2-GGUF)
49
 
50
  ### CHIMERA
51
  *Coming soon* — reasoning-focused models with explicit self-correction and agent trace supervision.