Tensorbend model library

Model catalog.

48 repositories: 37 public, 11 private. Search by upstream lab, model family, method, access, and date.

48 total repositories37 public11 private

All models

37 public · 11 private

Hugging Face

Complete model index.

Ex0bit account snapshot · 14 July 2026.

Treatment
48 of 48 repositories
Model familyQwen3.6Qwen5 artifactsPRISM-PROPRISMPRISM-DQLatest
Model familyqscopeTensorbend1 artifactOtherLatest
Model familyGLM-5.2Z.ai1 artifactPRISM-PROLatest
Model familyMiniMax M3MiniMax1 artifactPRISM-PROLatest
Model familyDeepSeek V4 ProDeepSeek2 artifactsPRISM-PROLatest
Model familyDeepSeek V4 FlashDeepSeek1 artifactPRISM-PROLatest
Model familyMiniMax SLURPYMiniMax2 artifactsPRISM-DQOtherLatest
Model familyGemma 4Google2 artifactsPRISM-PROPRISM-DQLatest
Model familyMYTHOS / Gemma 4Google1 artifactPRISM-PROPRISM-DQLatest
Model familyJIT LoRATensorbend1 artifactOtherLatest
Model familyQwen3.5Qwen5 artifactsPRISM-PROPRISMPRISM-LITEPRISM-DQLatest
Model familyStep 3.5 FlashStepFun4 artifactsPRISM-PROPRISMLatest
Model familyMiniMax M2.5MiniMax5 artifactsPRISM-PROPRISM-LITELatest
Model familyKimi K2.5Moonshot AI2 artifactsPRISMLatest
Model familyGLM-4.7 FlashZ.ai1 artifactPRISMLatest
Model familyLFMLiquid AI1 artifactPRISMLatest
Model familyMiniMax M2.1MiniMax2 artifactsPRISMOtherLatest
Model familyGLM-4.7Z.ai1 artifactPRISMLatest
Model familyNemotron 3 NanoNVIDIA2 artifactsPRISMLatest
Model familyGLM-4.6V FlashZ.ai1 artifactPRISMLatest
Model familyINTELLECT-3Prime Intellect1 artifactPRISMLatest
Model familyOLMo 3AI23 artifactsOtherLatest
Model familyQwen3-VLTOQwen2 artifactsOtherLatest
Model familyHRMNot specified1 artifactOtherLatest
Open Ex0bit on Hugging Face

Release fields

Method / Artifact / Terms

Fields

Release metadata.

PRISM is an intervention. PRISM-DQ is quantization. Runtime, hardware, access, and license are listed with the repository.

01

Intervention class

PRISM / PRISM-LITE / PRISM-PRO

Behavioral intervention applied to a named base model.

02

Quantization method

PRISM-DQ

Sensitivity-aware precision assignment by tensor class.

03

Format, runtime, precision

GGUF / safetensors · MLX / llama.cpp / SGLang · NVFP4 / FP8 / INT4

Artifact container, execution stack, and numerical representation.

04

Architecture and systems work

Dense / MoE / multimodal · EAGLE-3 / native MTP / REAP

Base architecture and applied acceleration or compression method.

05

Model family

Qwen / Gemma / MiniMax / Kimi / StepFun / GLM / Nemotron / OLMo / Prime Intellect / LFM

Upstream weights and lineage.

06

Access and license

Open / gated / member / one-time / quote-based

Download terms and commercial rights.

Access

Open / Gated / Paid / Contract

Terms

Model access.

Public weights · Available now · $0

Open download.

Weights, model card, deployment notes, and artifact license.

Browse public downloads ↗

Commercial use · Scoped · Quote-based

Commercial scope.

Base weights, method, target hardware, evaluation, and operating rights.

Commission a model build ↗

One-time listings

Model card, deliverable, license, price, and Ko-fi checkout.

Rights follow the artifact license and upstream base-model license.