Commercial-Safe Apache 2.0 & MIT Open-Source AI Models Index (2026)

01

●LOCAL • 94/100

Alibaba / Qwen

Alibaba Qwen's flagship open-weight coding model with 32.5B dense parameters, supporting a 128K context window with verified state-of-the-art Python, TypeScript, and multi-language code generation.

BASE ARCHITECTURE / Qwen2.5-Coder-32B-Instruct

BRuns well (61/100) • Q4_K_M (~35 tok/s • 4GB free)

ℹTHE BRUTAL TRUTH

The premier open coding model for local developers. If you have a 24GB GPU, it delivers frontier coding assistance with zero API fees.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Refactor this service into typed modules and generate integration tests.

PREVIEW NOTE

Production-ready typed code implementation with complete unit tests.

1,120

Hugging Face↗

02

●LOCAL • 96/100

DeepSeek-V3 671B (Local MoE)

DeepSeek

The flagship 671B total / 37B active Mixture-of-Experts foundation model with Multi-head Latent Attention (MLA), matching closed frontier models under MIT license.

BASE ARCHITECTURE / DeepSeek-V3 (671B MoE)

FToo heavy (11/100) • Needs 48GB at IQ2_XS

Rent a Cloud GPU•$0.14/hr›

ℹTHE BRUTAL TRUTH

The biggest open-weight breakthrough in history. If you have 64GB-128GB unified memory or a dual-GPU node, it replaces your entire cloud API bill under MIT.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Analyze the architectural latency trade-offs between Multi-Head Attention and Multi-head Latent Attention (MLA).

PREVIEW NOTE

A rigorous mathematical analysis comparing KV-cache memory consumption and matrix compression ratios.

1,040

Hugging Face↗

03

●LOCAL • 90/100

Qwen2.5-14B-Instruct

Alibaba / Qwen

Alibaba Qwen's high-efficiency 14.7B dense instruction-tuned model with 128K context, hitting the sweet spot for 12GB–16GB consumer GPUs.

BASE ARCHITECTURE / Qwen2.5-14B-Instruct

SRuns well (85/100) • Q4_K_M (~71 tok/s • 14GB free)

ℹTHE BRUTAL TRUTH

The best quality-per-GB model on 12GB–16GB consumer hardware. Outstanding balance of speed and coding capability under Apache 2.0.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Build a typed API client with retries and unit tests.

PREVIEW NOTE

Complete TypeScript client with retry logic and unit tests.

940

Hugging Face↗

04

●LOCAL • 82/100

Wan 2.1 14B

Wan / Alibaba

Wan-AI's official 14B open-weight video foundation model for text-to-video and image-to-video generation, with native ComfyUI and Comfy-Org modular workflow repacks.

BASE ARCHITECTURE / Wan 2.1 14B (T2V / I2V Diffusion Transformer)

SRuns well (100/100) • GGUF Q4 (~118 tok/s • 18GB free)

ℹTHE BRUTAL TRUTH

The most accessible open video foundation model released to date. Apache 2.0 with modular Comfy-Org safetensors and low-VRAM GGUF builds.

No cardLocalComfyUIComfy-Org RepackOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

A slow cinematic tracking shot across a rain-soaked neon street.

PREVIEW NOTE

Photorealistic 720p cinematic video sequence.

Original Author:Wan-AI/Wan2.1-T2V-14B ↗

Comfy-Org Repack:Comfy-Org/Wan_2.1_ComfyUI_repackaged ↗

2450k

Comfy-Org Hugging Face↗

05

●LOCAL • 94/100

Qwen2.5-72B-Instruct

Alibaba / Qwen

Alibaba's 72B general-purpose open-weight titan with 128K context. Ranked top 3 globally across all open foundation models with Apache 2.0 licensing.

BASE ARCHITECTURE / Qwen2.5-72B-Instruct

FToo heavy (13/100) • Needs 42GB at Q4_K_M

Rent a Cloud GPU•$0.14/hr›

ℹTHE BRUTAL TRUTH

The most powerful general-purpose Apache 2.0 model on earth. If you have 48GB VRAM or a 64GB Mac, it out-reasons Llama 3.3 without legal strings.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Analyze the geopolitical implications of rare earth mineral export restrictions on semiconductor supply chains.

PREVIEW NOTE

A multi-dimensional economic and diplomatic analysis examining processing bottlenecks and alternative refining technologies.

920

Hugging Face↗

06

●LOCAL • 95/100

Whisper Large v3 Turbo

OpenAI

OpenAI's latest optimized automatic speech recognition (ASR) model. Delivers 8x faster transcription with near-zero word error rate under MIT license.

BASE ARCHITECTURE / Whisper Large v3 Turbo

SRuns well (97/100) • FP16 (~176 tok/s • 20GB free)

ℹTHE BRUTAL TRUTH

The absolute undisputed king of speech-to-text. 8x faster than before, runs in 4GB VRAM, and carries a pure MIT license. Stop paying for Whisper APIs.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Transcribe an hour-long multi-speaker meeting with timestamps and punctuation.

PREVIEW NOTE

A precise JSON transcript with segment timestamps, speaker pauses, and accurate casing.

910

Hugging Face↗

07

●LOCAL • 89/100

Qwen2.5-Coder-7B-Instruct

Alibaba / Qwen

State-of-the-art 7B code LLM rivaling older 34B models. Fits on virtually any 6GB–8GB GPU with 128K context and Apache 2.0 licensing.

BASE ARCHITECTURE / Qwen2.5-Coder-7B-Instruct

SRuns well (98/100) • Q4_K_M (~141 tok/s • 19GB free)

ℹTHE BRUTAL TRUTH

The absolute king of 8GB GPUs for coding. It beats models four times its size, runs at 80 tok/s on an RTX 3060, and carries Apache 2.0.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Write a SQL migration script to add soft deletes and index created_at on user tables.

PREVIEW NOTE

A PostgreSQL migration script adding deleted_at TIMESTAMP WITH TIME ZONE and a partial index.

840

Hugging Face↗

08

●LOCAL • 80/100

HunyuanVideo (13B)

Tencent

Tencent's frontier 13B dual-stream diffusion transformer for video generation. Produces photorealistic 720p/1080p cinematic video rivaling proprietary models under Apache 2.0.

BASE ARCHITECTURE / HunyuanVideo (13B)

BRuns well (58/100) • GGUF Q4 (~39 tok/s • 6GB free)

ℹTHE BRUTAL TRUTH

The Sora of open source. If you have an RTX 4090 or A6000, the video fidelity destroys everything else on the open market under Apache 2.0.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

A macro shot of a chameleon's eye rotating and focusing on a dewdrop on a tropical leaf.

PREVIEW NOTE

A photorealistic 1080p video sequence showing microscopic iris contraction and translucent dew reflections.

820

Hugging Face↗

09

●LOCAL • 90/100

FLUX.1 Schnell

Black Forest Labs

A fast text-to-image model variant with an Apache 2.0 license, designed for rapid iteration and local ComfyUI workflows.

BASE ARCHITECTURE / Black Forest Labs FLUX.1 Schnell

SRuns well (93/100) • GGUF Q4 (~88 tok/s • 16GB free)

ℹTHE BRUTAL TRUTH

Apache 2.0 + 8GB minimum + fast enough for real iteration is the open image sweet spot right now. FP8 quality beats most hosted alternatives at low cost.

No cardLocalComfyUIComfy-Org RepackAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Editorial still life of a glass sculpture in hard morning light.

PREVIEW NOTE

Illustrative image prompt; this page does not render images.

Original Author:black-forest-labs/FLUX.1-schnell ↗

Comfy-Org Repack:Comfy-Org/flux1-schnell ↗

7200k

Comfy-Org Hugging Face↗

10

●LOCAL • 91/100

Phi-4 14B

Microsoft

Microsoft's synthetic-data trained 14B reasoning powerhouse. Outperforms many 70B models on math, STEM logic, and structured evaluation under MIT license.

BASE ARCHITECTURE / Phi-4 (14B dense)

SRuns well (85/100) • Q4_K_M (~78 tok/s • 15GB free)

ℹTHE BRUTAL TRUTH

A synthetic data triumph. If you need math, logic, or STEM reasoning on a 12GB card, Phi-4 crushes models twice its size under a pure MIT license.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Prove by mathematical induction that 1 + 2 + ... + n = n(n + 1)/2 for all natural numbers n.

PREVIEW NOTE

A formal mathematical proof establishing the base case n=1 and the inductive step k -> k+1.

790

Hugging Face↗

11

●LOCAL • 78/100

CogVideoX-5B

THUDM / Zhipu AI

Open-source 3D video diffusion transformer with 3D VAE and expert transformer blocks, generating 720p 6-second cinematic video clips under Apache 2.0.

BASE ARCHITECTURE / CogVideoX-5B (T2V / I2V)

ARuns well (81/100) • INT8 GGUF (~59 tok/s • 12GB free)

ℹTHE BRUTAL TRUTH

A landmark in open video generation. Wan 2.2 is easier on low VRAM, but CogVideoX-5B has exceptional motion fluidity on 24GB rigs.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

A drone shot flying through a waterfall into a lush hidden cave at sunset.

PREVIEW NOTE

A 6-second 720p video sequence showing mist particles and gradual exposure transition into the cavern.

750

Hugging Face↗

12

●LOCAL • 85/100

DeepSeek-R1-Distill-32B

DeepSeek

A distilled reasoning model that preserves chain-of-thought behaviour in a size that fits on a 24 GB GPU at 4-bit.

BASE ARCHITECTURE / DeepSeek-R1-Distill 32B

BRuns well (61/100) • Q4_K_M (~35 tok/s • 4GB free)

ℹTHE BRUTAL TRUTH

MIT license + real reasoning traces + fits in 24GB is a rare combo. Watch token burn — reasoning uses 3-5x more output tokens than a normal model.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Explain the trade-offs between RAG and long-context retrieval for a 200K-token corpus.

PREVIEW NOTE

Illustrative reasoning prompt; not executed here.

741

Hugging Face↗

13

●LOCAL • 88/100

Mistral-Nemo-12B-Instruct

Mistral AI & NVIDIA

Co-developed by Mistral and NVIDIA, this 12B model features Tekken tokenization, a 128K context window, and full Apache 2.0 licensing, fitting easily in 8GB–12GB VRAM.

BASE ARCHITECTURE / Mistral-Nemo-Instruct-2407 (12B)

SRuns well (92/100) • Q4_K_M (~88 tok/s • 16GB free)

ℹTHE BRUTAL TRUTH

The best 12B model in existence. Tekken tokenizer encodes multilingual text with 30% fewer tokens, and it carries true Apache 2.0.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Act as a customer support triage agent: categorize this dispute, identify billing errors, and propose an adjustment.

PREVIEW NOTE

A structured agent evaluation with triage severity, account calculation checks, and credit adjustments.

740

Hugging Face↗

14

●LOCAL • 83/100

SmolLM2-1.7B-Instruct

Hugging Face

Ultra-compact on-device language model trained on 11 trillion tokens by Hugging Face. Runs at 120+ tokens/sec on CPU or 2GB VRAM with Apache 2.0.

BASE ARCHITECTURE / SmolLM2-1.7B-Instruct

SRuns well (94/100) • Q4_K_M (~220 tok/s • 22GB free)

ℹTHE BRUTAL TRUTH

The best sub-2B model in the world. Ideal for edge IoT, Raspberry Pis, and instant regex/JSON extraction at 120+ tok/s on CPU.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Extract customer name, order ID, and refund reason into clean JSON from this email.

PREVIEW NOTE

A structured JSON object with parsed customer fields and zero markdown conversational filler.

710

Hugging Face↗

15

●LOCAL • 88/100

LTX-Video (2B Realtime)

Lightricks

Real-time 2B spatial-temporal video DiT capable of generating 24fps high-resolution video in under 15 seconds on consumer GPUs under Apache 2.0.

BASE ARCHITECTURE / LTX-Video 0.9.1 (2B)

ARuns well (79/100) • BF16 (~78 tok/s • 15GB free)

ℹTHE BRUTAL TRUTH

Generates 24fps video in seconds instead of minutes. On an 8GB card, it feels like magic compared to the painful wait times of older video models.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

A golden retriever running through autumn leaves in slow motion.

PREVIEW NOTE

A 24fps video sequence rendered in under 18 seconds with smooth fur movement and flying leaves.

710

Hugging Face↗

16

●LOCAL • 86/100

Mistral Small 3

Mistral AI

A 24B Apache-2.0 model tuned for speed and local agentic loops, fitting in 16 GB at 4-bit for real-time workflows.

BASE ARCHITECTURE / Mistral Small 3 (24B)

ARuns well (78/100) • Q4_K_M (~47 tok/s • 9GB free)

ℹTHE BRUTAL TRUTH

The only sub-16GB model on this list that runs real-time agent loops. Trade: weaker reasoning than 27B+ models.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

When a new lead arrives, enrich the record and route it to the right owner.

PREVIEW NOTE

Illustrative automation prompt; credentials are not connected.

699

Hugging Face↗

17

●LOCAL • 92/100

Qwen2.5-Math-72B-Instruct

Alibaba / Qwen

World-leading open mathematical reasoning model, scoring over 85% on MATH benchmarks. Specialized for scientific computation, equations, and formal proofs.

BASE ARCHITECTURE / Qwen2.5-Math-72B-Instruct

FToo heavy (13/100) • Needs 42GB at Q4_K_M

Rent a Cloud GPU•$0.14/hr›

ℹTHE BRUTAL TRUTH

The absolute gold standard for mathematical precision in the open ecosystem. Don't use it for chat — use it for proofs and numeric analysis.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Find all integers n such that n^4 + 4 is a prime number, with full proof.

PREVIEW NOTE

A formal Sophie Germain identity factorization showing n=1 is the only valid solution.

680

Hugging Face↗

18

●LOCAL • 84/100

Kokoro-82M

Kokoro / community

A compact 82M text-to-speech model suited to local audio pipelines, CPU inference, and lightweight browser prototypes.

BASE ARCHITECTURE / Kokoro-82M

SRuns well (95/100) • ONNX CPU (~220 tok/s • 22GB free)

ℹTHE BRUTAL TRUTH

Runs on CPU, tiny footprint, Apache 2.0 — the only reason not to use it is voice quality. If you need premium voices, pay for ElevenLabs.

No cardLocalOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Welcome back. Your next idea starts here.

PREVIEW NOTE

Illustrative speech text; no audio is generated by this page.

632

Hugging Face↗

19

●LOCAL • 86/100

InternLM2.5-20B-Chat

Shanghai AI Lab

A 20B parameter model featuring an astounding 1-million-token native context window. Designed for book-length document reasoning and complex agent tools.

BASE ARCHITECTURE / InternLM2.5-20B-Chat

ARuns well (77/100) • Q4_K_M (~54 tok/s • 11GB free)

ℹTHE BRUTAL TRUTH

The only sub-24GB model with a verified 1M context window that doesn't hallucinate past 64K. Watch your KV-cache memory at full lengths.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Search a 500-page codebase transcript for all references to deprecated API route /v1/auth/legacy.

PREVIEW NOTE

A structured cross-reference table indexing timestamps, filenames, and replacement routes.

620

Hugging Face↗

20

●LOCAL • 86/100

Kolors

Kuaishou Technology

Diffusion model based on SDXL and ChatGLM3 text encoding, supporting both English and Chinese text rendering with realistic skin textures and lighting.

BASE ARCHITECTURE / Kolors (2.7B)

ARuns well (79/100) • FP8 (~71 tok/s • 14GB free)

ℹTHE BRUTAL TRUTH

Incredible portrait fidelity and bilingual typography. ChatGLM3 text encoder handles nuances that CLIP misses completely.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

A hyper-detailed traditional porcelain craftsman shaping clay in a sunlit Beijing workshop.

PREVIEW NOTE

A lifelike portrait showing clay splatters on artisan fingers and delicate natural ambient lighting.

610

Hugging Face↗

21

●LOCAL • 85/100

AuraFlow-v0.3

fal.ai

An open-source 6.8B parameter text-to-image diffusion transformer model by fal.ai, released under Apache 2.0 with linear attention and fast inference.

BASE ARCHITECTURE / AuraFlow-v0.3 (6.8B)

ARuns well (82/100) • FP8 (~59 tok/s • 12GB free)

ℹTHE BRUTAL TRUTH

A very clean, royalty-free Apache 2.0 DiT. If you dislike Stability's license terms and need an alternative to FLUX, AuraFlow is a real option.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Abstract architectural composition of intersecting glass planes in desert haze.

PREVIEW NOTE

A sharp geometric rendering featuring realistic atmospheric refraction and minimalist shadows.

580

Hugging Face↗

22

●LOCAL • 88/100

MOSS Image Base

OpenMOSS Team

User guide   ·   中文用户指南   ·   ComfyUI

BASE ARCHITECTURE / MOSS Image Base (5.1B Flow-Matching Diffusion Transformer)

SRuns well (97/100) • Q2_K (2-bit Extreme) (~220 tok/s • 22GB free)

ℹTHE BRUTAL TRUTH

Audited in Stactora CMS. Architecture verified with 5.1B parameters.

No cardLocalComfyUIComfy-Org RepackOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

A wide view of a refrigerator beside a kitchen counter with a fruit bowl and a sticky note.

PREVIEW NOTE

Photorealistic generative composition with clear embedded typography.

Original Author:OpenMOSS-Team/MOSS-Image-Base ↗

Comfy-Org Repack:Comfy-Org/MOSS-Image ↗

168k

Comfy-Org Hugging Face↗

23

●LOCAL • 96/100

Clover 35B A3B (Diffusion LLM)

DiffuSpace / HKU NLP

DiffuSpace's breakthrough Diffusion Language Model (dLLM). Replaces traditional autoregressive token generation with parallel block diffusion denoising across 35B MoE parameters (3B active), shattering SWE-bench Verified coding tasks.

BASE ARCHITECTURE / Clover-35B-A3B-Preview (Block Diffusion MoE)

ARuns well (79/100) • Q4_K_M (~47 tok/s • 9GB free)

ℹTHE BRUTAL TRUTH

The first true demonstration that diffusion language models can beat autoregressive models on real SWE-bench coding. Parallel denoising means complete code functions appear in bursts rather than token-by-token trickles.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Synthesize an entire concurrent network driver in Rust with memory-safe buffer management.

PREVIEW NOTE

Parallel-generated Rust implementation verified through multi-token diffusion steps.

540

Hugging Face↗

24

●LOCAL • 85/100

Granite-3.0-8B-Instruct

IBM Research

IBM's flagship enterprise open-weight model with 128K context, trained under strict copyright curation and released with full Apache 2.0 licensing and IP indemnity.

BASE ARCHITECTURE / Granite-3.0-8B-Instruct

SRuns well (98/100) • Q4_K_M (~141 tok/s • 19GB free)

ℹTHE BRUTAL TRUTH

Built specifically for enterprise legal departments terrified of training data copyright lawsuits. Solid RAG performance with true Apache 2.0.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Draft an enterprise compliance policy for data classification across Confidential, Internal, and Public.

PREVIEW NOTE

A formal compliance document with handling procedures, access controls, and retention schedules.

530

Hugging Face↗

25

●LOCAL • 98/100

Audio8-TTS Realistic 0.6B

Edge0

Edge0's ultra-realistic 601M parameter open-weight Text-to-Speech and zero-shot voice cloning model. Bundles an integrated 44.1kHz neural audio codec and 23-language multilingual synthesis under Apache 2.0.

BASE ARCHITECTURE / Audio8-TTS-Realistic-0.6b (DualAR Architecture)

SRuns well (92/100) • INT8 (~220 tok/s • 23GB free)

ℹTHE BRUTAL TRUTH

One of the cleanest sub-1B TTS engines in the open-source ecosystem. Bundles its own 44.1kHz neural codec, clones voices in 3 seconds, and runs on literally any 2GB laptop GPU under Apache 2.0.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Clone this 5-second speaker reference and synthesize technical documentation narration.

PREVIEW NOTE

Studio-grade 44.1kHz stereo audio stream with accurate speaker timbre and cadence.

510

Hugging Face↗

26

●LOCAL • 89/100

SenseNova 6.8 Code2Video 27B

SenseTime / SenseNova

SenseTime's 27B code-driven video synthesis model. Generates kinetic typography, data charts, and animations by producing and executing code with a 512K context window under Apache 2.0.

BASE ARCHITECTURE / SenseNova-6.8-Code2Video (27B Qwen Hybrid)

BRuns well (60/100) • Q4_K_M (~39 tok/s • 6GB free)

ℹTHE BRUTAL TRUTH

A brilliant paradigm shift in AI video: instead of hallucinating blurry pixels, it writes code that renders pixel-perfect animations. Every single frame is mathematically crisp, fully inspectable, and editable line-by-line.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Generate a dynamic 30-second kinetic typography and data visualization animation showcasing market trends.

PREVIEW NOTE

Full executable code spec with timed motion keyframes and contact sheet verification.

470

Hugging Face↗

27

●LOCAL • 98/100

Spark X2.6 1.7B

SparkLLM Team / XHToken

XHToken's state-of-the-art 1.7B on-device reasoning and coding model. Features a 1M token context length, configurable thinking effort modes (none/low/high), and outsized performance on SWE-bench and autonomous planning.

BASE ARCHITECTURE / Spark-X2.6-1.7B (Sliding-Attention Transformer)

SRuns well (94/100) • Q4_K_M (~220 tok/s • 22GB free)

ℹTHE BRUTAL TRUTH

The undisputed champion of 1.7B on-device reasoning. Having a controllable thinking budget (none/low/high) plus a 1M token context under Apache 2.0 makes it the best lightweight agent brain available.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Analyze this 20-file repo trace, identify the race condition, and output a minimal patch.

PREVIEW NOTE

Step-by-step thinking trace followed by precise diff patch.

460

Hugging Face↗

28

●LOCAL • 93/100

Groot 19B A3B

GrootTeam

GrootTeam's native multimodal vision-language Mixture-of-Experts model. Packs 19B total parameters activating only 3B per token, delivering 256K context visual reasoning, image understanding, and tool execution on consumer GPUs.

BASE ARCHITECTURE / Groot-19B-A3B-261023 (Multimodal MoE Architecture)

SRuns well (86/100) • Q4_K_M (~64 tok/s • 13GB free)

ℹTHE BRUTAL TRUTH

The sweet-spot vision-language model for 12GB and 16GB GPUs. Activating only 3B parameters per token gives you lightning-fast chart and UI analysis without the latency hit of dense vision models.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Inspect this architecture blueprint and financial chart; verify structural data points.

PREVIEW NOTE

Comprehensive visual analysis with extracted data tables and logic verification.

430

Hugging Face↗

29

●LOCAL • 91/100

IDOL (Image-to-3D DiT)

Speridlabs

Speridlabs' open-source 3D Diffusion Transformer (3D-DiT). Converts single photos into dense 3D Gaussian Splats (up to 1,048,576 Gaussians) outputting standard .ply files under an Apache 2.0 license.

BASE ARCHITECTURE / IDOL 3D-DiT (0.66B Generator / 1.8B Pipeline)

SRuns well (92/100) • FP8 (~123 tok/s • 18GB free)

ℹTHE BRUTAL TRUTH

The most practical open-weight 3D Gaussian generator today. Requiring only ~7.2 GB VRAM under Apache 2.0 makes high-fidelity 3D spatial generation accessible on standard laptops and desktops.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Generate a dense 3D Gaussian Splat from an isolated product photograph.

PREVIEW NOTE

Exported 1,048,576 Gaussian splat .ply asset ready for web viewers and game engines.

420

Hugging Face↗

30

●LOCAL • 92/100

Nanbeige 4.3 33B

Nanbeige LLM Lab

Nanbeige's flagship 33B dense language and coding model with a 512K context window. Engineered specifically for agentic terminal workflows, SWE-bench engineering, and professional enterprise co-work under Apache 2.0.

BASE ARCHITECTURE / Nanbeige4.3-33B (Dense Teacher Architecture)

DDecent (36/100) • Q4_K_M (~21 tok/s • 3GB free)

ℹTHE BRUTAL TRUTH

A serious alternative to Qwen2.5-Coder-32B built specifically for autonomous agents that run terminal commands and refactor full repos. If you run SWE-bench agents on a 24GB card, this is a top-tier driver.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Diagnose this failing CI pipeline across 4 microservices and execute terminal fixes.

PREVIEW NOTE

Step-by-step reasoning trace with verified terminal commands and patch files.

410

Hugging Face↗

31

●LOCAL • 91/100

Apex 35B V1.0

Apex Intelligence

Apex Intelligence's 35B MoE language model trained via recursive automated AI research agents. Specialized in computational science, robotics simulation, Claude Code agent workflows, and deep scientific reasoning.

BASE ARCHITECTURE / Apex-35B-V1.0 (Automated Research MoE Architecture)

ARuns well (79/100) • Q4_K_M (~47 tok/s • 9GB free)

ℹTHE BRUTAL TRUTH

Trained by AI agents to perform AI and scientific research. Because only 3B parameters are active per token, it runs like a 3B model while delivering the deep reasoning depth of a 35B architecture on 16GB GPUs.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Formulate a robotics trajectory optimization algorithm with obstacle avoidance constraints.

PREVIEW NOTE

Rigorous mathematical formulation with typed Python simulation code.

390

Hugging Face↗

Commercial-Safe Apache 2.0 & MIT Open-Source AI Models Index (2026)

Frequently Asked Questions · /license/apache-2