Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
GLM-5.3-SLIM-GGUF
Modelstext generation model by Scantist
Scantist/GLM-5.3-SLIM-GGUF -
GLM5.3-Flash-E224-DGX-Spark
Modelsimage text to text model by autotrust · vllm
autotrust/GLM5.3-Flash-E224-DGX-Spark -
GLM5.3-Flash-E192-DGX-Spark
Modelsimage text to text model by autotrust · vllm
autotrust/GLM5.3-Flash-E192-DGX-Spark -
GLM5.3-Flash-E256-DGX-Spark
Modelsimage text to text model by autotrust · vllm
autotrust/GLM5.3-Flash-E256-DGX-Spark -
Qwen: Qwen3 30B A3B
ModelsQwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
qwen/qwen3-30b-a3b -
NVIDIA: Nemotron 3 Ultra
ModelsNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
nvidia/nemotron-3-ultra-550b-a55b -
StepFun: Step 3.5 Flash
ModelsStep 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
stepfun/step-3.5-flash -
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
nvidia/nemotron-3-ultra-550b-a55b:free -
MoonshotAI: Kimi K2 Thinking
ModelsKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
moonshotai/kimi-k2-thinking -
MiniMax: MiniMax M1
ModelsMiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
minimax/minimax-m1 -
DeepSeek: DeepSeek V3.2 Exp
ModelsDeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
deepseek/deepseek-v3.2-exp -
Meta: Llama 3.2 3B Instruct
ModelsLlama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...
meta-llama/llama-3.2-3b-instruct -
StepFun: Step 5 Preview
ModelsStep 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...
stepfun/step-5-preview -
OpenAI: gpt-oss-20b
Modelsgpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
openai/gpt-oss-20b -
Meta: Llama 4 Maverick
ModelsLlama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
meta-llama/llama-4-maverick -
KT: Mi:dm K 3.0 Pro
ModelsMi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.
kt/midm-k-3.0-pro -
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
mistralai/mistral-large-2512 -
OpenAI: gpt-oss-20b (batch)
Modelsgpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
openai/gpt-oss-20b:batch -
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
reflection/beam-1.0-501b-a23b -
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
deepseek/deepseek-v4.1-flash -
Qwen: Qwen3.5-Flash
ModelsThe Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...
qwen/qwen3.5-flash-02-23 -
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
deepseek/deepseek-v4.1-flash:batch -
Qwen: Qwen3.6 Plus
ModelsQwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...
qwen/qwen3.6-plus -
Qwen: Qwen3.5-9B
ModelsQwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
qwen/qwen3.5-9b
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.