AITrending catalog

Models

Explore model access, licenses and capabilities.

155 models indexed

155 models

About signals
R
Model Nov 4, 2026
Ricursive announcement video frame charts its reported Terminal-Bench 2.1 score against total model parameter counts.

Ripple-65B Preview

A dense 65B open-weight model with BF16, NVFP4 and base checkpoints; Ricursive reports strong agentic coding results and up to one million tokens of context.

By
Ricursive Intelligence
Access
Not recorded
License
Not recorded
Deployment
Not recorded
Signal source-backed
coding-agentsself-hosted 4 sources
Q
Model Nov 3, 2026

Qwen3.5-4B Uncensored Browser GGUF

InterpreticAI's 1.86 GB IQ3_XXS quantization targets browser and mobile inference, with author-reported losses in general capability and more degenerate answers.

By
Not recorded
Access
Public GGUF files; the author targets browser and mobile runtimes and supplies llama.cpp usage. Image input requires a separate projector and compatible runtime.
License
Apache-2.0
Deployment
Not recorded
Signal source-backed
self-hostedmultimodal 2 sources
M
Model Nov 2, 2026

Moebius Inpaint GGUF

Experimental community GGUF conversions of Moebius image-inpainting weights for CrispEmbed's native engine, with four published precision variants.

By
cstr; upstream Moebius by hustvl
Access
Public GGUF downloads; requires the experimental CrispEmbed native inpainting engine and matching SDXL VAE
License
Upstream records differ between Apache-2.0 and MIT for weights; publisher preserves both without claiming dual licensing
Deployment
Not recorded
Signal source-backed
self-hosted 2 sources
P
Model Oct 29, 2026
Author-published generated dog clips side by side, labeled Pika H3 Flex official six steps and Flex Turbo LoRA four steps.

Pika H3 Flex Turbo LoRA

akhaliq's community fusion of Pika H3 Flex and LightX2V MiniMax-H3 Turbo adapters, offered as four-step and eight-step LoRAs for local video with audio.

By
akhaliq
Access
Downloadable FL2VA and Ref2VA LoRAs for an existing MiniMax-H3 setup; four-step, eight-step and rank-32 lite files.
License
MiniMax H3 Community License Agreement; model-derivative terms apply.
Deployment
Not recorded
Signal source-backed
self-hostedmultimodal 2 sources
Q
Model Oct 21, 2026
Turboderp's Qwen3.8-Flash-Next chart compares mean KL divergence against bits per weight for EXL3, self-calibrated EXL3, GGUF and NVFP4 configurations.

Qwen3.8-Flash-Next EXL3

Community EXL3 quantizations of Qwen3.8-Flash-Next, including a self-calibrated 1.66bpw branch whose author claims single-RTX-5090 agentic inference with a 64K quantized cache.

By
turboderp
Access
Downloadable EXL3 branches for compatible local inference; smallest branch uses mixed tensor precisions and a separately stored n-gram table.
License
Qwen Community License 1.0; commercial service and AI Work Assistant restrictions apply.
Deployment
Not recorded
Signal source-backed
self-hostedcoding-agents 3 sources
N
Model Oct 21, 2026
NVIDIA's Kumo Relational architecture diagram links users, orders and items, then applies attention within and across tables.

NVIDIA Kumo Relational

A pretrained relational foundation model for classification and regression across linked tables using historical labeled examples as inference context.

By
NVIDIA
Access
Downloadable weights through structured-data-models; GPU inference and a separate NVIDIA NIM serving route are documented.
License
OpenMDW 1.1 for weights; the NVIDIA-authored inference library code is Apache 2.0.
Deployment
Downloadable weights
Signal source-backed
decision-modelsself-hosted 3 sources
R
Model Oct 21, 2026
NVIDIA's AtomWorks Studio screenshot shows the annotated PD-L1 target, binder length specification and hotspot panel before protein generation.

RFD4-Proteina

A joint protein-sequence and all-atom structure generation model from the University of Washington's Institute for Protein Design and NVIDIA GenAIR.

By
Baker Lab, Institute for Protein Design, University of Washington / NVIDIA GenAIR
Access
Downloadable weights and browser Spaces
License
BSD-3-Clause for model and weights; optional third-party assets have separate terms
Deployment
Downloadable weights
Signal source-backed
multimodalverification 2 sources
M
Model Oct 16, 2026
Hugging Face's oMLX Chat screenshot with Muse Spark Open selected and its reasoning effort control set to High.

Muse Spark Open

Meta's 816B-total, 42B-active mixture-of-experts model for coding and agentic work, with multimodal inputs and community GGUF quantizations.

By
Meta Superintelligence Labs
Access
Gated original weights; community GGUF variants are listed separately. Large-memory hardware and a compatible runtime are required.
License
Muse Model License, with usage, attribution and qualifying Model-as-a-Service revenue terms; not an unrestricted permissive license.
Deployment
Not recorded
Signal source-backed
multimodalself-hostedcoding-agents 3 sources
F
Model Oct 16, 2026

Feyospace S1 OBLITERATED weighted GGUF

Community weighted GGUF conversions of OBLITERATUS's refusal-modified 28B Feyospace cybersecurity model, with listed files from 11.0 to 22.5 GB.

By
mradermacher; parent modification by OBLITERATUS; original model by Feyospace Team at Vera Praxis
Access
Public downloadable weighted/imatrix GGUF files; runtime compatibility and memory overhead need separate checking.
License
Apache-2.0 declared by the conversion and OBLITERATUS model cards.
Deployment
Not recorded
Signal source-backed
self-hostedagent-security 2 sources
P
Model Oct 15, 2026
Daily's PhoneLLM Max Alpha 2 example conversation shows short reasoning sentences, a changed party size, a reservation tool call and an end-call tool call.

PhoneLLM Alpha 2

Pipecat's Mini and Max text models for voice-agent pipelines, with tool calling, Pipecat Flows training and short reasoning in Max.

By
Daily / Pipecat
Access
Downloadable Mini and Max weights, including quantized variants; local inference requires compatible NVIDIA hardware and serving software.
License
Mini declares BSD-2-Clause with continuing NVIDIA base-model terms; Max declares OpenMDW 1.1. Consult the individual checkpoint licenses.
Deployment
Not recorded
Signal source-backed
ai-agentsself-hosted 3 sources
G
Model Oct 15, 2026
IBM's conceptual Granite Switch illustration with a large base-model block and three smaller adapter blocks.

Granite Switch 4.1

IBM's modular 8B and 30B checkpoints combining Granite chat, Decision and Guardian activated LoRA adapters, and an English speech-to-text encoder in one serving endpoint.

By
IBM Research
Access
Downloadable 8B and 30B checkpoints for Transformers or vLLM; local serving and dependencies required.
License
Apache 2.0, as declared in the IBM model cards.
Deployment
Not recorded
Signal source-backed
decision-modelsself-hostedmultimodal 3 sources
F
Model Oct 15, 2026
Author-generated FLUX 3 Klein sample pairs, with BF16 on the left and MXFP8 on the right: a sunflower portrait, a dog and a Tokyo street.

FLUX 3 Klein MXFP8 by FP8Enjoyer

A community MXFP8 conversion of the distilled FLUX 3 Image Klein transformer for ComfyUI, with laptop timings, paired samples and a compatibility patch.

By
FP8Enjoyer; original model by Black Forest Labs
Access
Downloadable ComfyUI-native Safetensors diffusion transformer; matching text encoder and VAE are separate.
License
FLUX Kommunity License v1.0; derivative restrictions and conditional commercial-output terms remain applicable.
Deployment
Not recorded
Signal source-backed
multimodalself-hosted 2 sources
E
Model Oct 15, 2026

EmbeddingGemma 2 0.8 BPW Multimodal

lethalbeats' community EmbeddingGemma 2 quantization with a 73.82 MB weight file, a custom CPU PyTorch loader and author-reported multimodal inference.

By
lethalbeats
Access
Downloadable packed weights with an included custom CPU PyTorch loader; tokenizer files and dependencies are additional.
License
The community model card declares Apache 2.0.
Deployment
Not recorded
Signal source-backed
multimodalself-hosted 2 sources
F
Model Oct 15, 2026
Hugging Face's generated knitted knight and dragon scene, with red boxes marking the knight's source and destination positions.

FLUX 3 Image Klein

Black Forest Labs' downloadable image-generation and editing model, with a 5.6B image transformer, multiple references and prompt-based layout boxes.

By
Black Forest Labs
Access
Downloadable base and distilled weights with gated file access; hosted BFL API and a Hugging Face demo.
License
FLUX Kommunity License v1.0; non-commercial uses and a conditional commercial-output exception below USD5 million gross annualized revenue including affiliates.
Deployment
Not recorded
Signal source-backed
multimodalself-hosted 4 sources

Compare models