Chroma's picture

Chroma

Chroma111

·

AI & ML interests

None yet

Recent Activity

liked a model about 23 hours ago

lightx2v/Wan2.1-Distill-Loras

liked a model about 23 hours ago

lightx2v/Encoders

liked a model about 23 hours ago

lightx2v/Wan2.2-Official-Models

View all activity

Organizations

None yet

upvoted 7 collections 2 days ago

Deepseek V3 (All Versions)

Deepseek-V3-0324 and V3 - available in original, and Dynamic GGUF formats, with support for 2-8-bit quantized versions. • 7 items • Updated 4 days ago • 39

Gemma 3

All versions of Google's new multimodal models including QAT in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 55 items • Updated 4 days ago • 96

DeepSeek-V3.1

DeepSeek's new 3.1 update to their V3 models! • 6 items • Updated 4 days ago • 7

DeepSeek R1 (All Versions)

DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 37 items • Updated 4 days ago • 261

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 79 items • Updated 4 days ago • 240

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 59 items • Updated 4 days ago • 258

Ministral 3

Mistral Ministral 3: new multimodal models in Base, Instruct, and Reasoning variants, available in 3B, 8B, and 14B sizes. • 28 items • Updated 3 days ago • 19

upvoted a collection 3 days ago

Skywork-R1V4

Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch • 2 items • Updated 1 day ago • 3

upvoted 2 collections 4 days ago

Ministral 3

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated 4 days ago • 110

Mistral Large 3

A state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. • 4 items • Updated 4 days ago • 69

upvoted a paper 5 days ago

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Paper • 2511.22699 • Published 9 days ago • 143

upvoted a collection 5 days ago

Z-Image

4 items • Updated 5 days ago • 70

upvoted a collection 7 days ago

Qwen3-Next

4 items • Updated Sep 22 • 161

upvoted a paper 8 days ago

MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

Paper • 2508.14879 • Published Aug 20 • 68

upvoted an article 8 days ago

Article

Norm-Preserving Biprojected Abliteration

29 days ago

•

48

upvoted 4 collections 8 days ago

RpR Models

RpR (RolePlay with Reasoning) models which are built on RPMax datasets with properly trained multi-turn reasoning. • 8 items • Updated Jun 25 • 16

Derestricted

Models abliterated using Norm-Preserving Biprojected Abliteration • 5 items • Updated 8 days ago • 11

DeepSeek-R1

10 items • Updated 9 days ago • 820

DeepSeek-V3

4 items • Updated 9 days ago • 277

upvoted a paper 8 days ago

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Paper • 2402.03300 • Published Feb 5, 2024 • 137