サイト内検索
AI モデル 84753
- neural-cherche-sparse-embed↗
raphaelsty
- gpt-oss-20b↗
RedHatAI
Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. We’re releasing two flavors of these open models: - `gpt-oss-120b` — for production, general purpose, high reasoning use cases that fit into a single 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters) - `gpt-oss-20b` — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters) Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.
- Qwen3.8-27B-MXFP4↗
RedHatAI
- abhinand_-_gemma-2b-it-tamil-v0.1-alpha-gguf↗
RichardErkhov
- Ejafa_-_phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5-gguf↗
RichardErkhov
- hahahafofo_-_Qwen-1_8B-Stable-Diffusion-Prompt-gguf↗
RichardErkhov
- harborwater_-_open-llama-3b-claude-30k-gguf↗
RichardErkhov
- YeungNLP_-_firefly-qwen1.5-en-7b-unsloth-gguf↗
RichardErkhov
- Kimi-K2.7-Code-MLX-3.6bit↗
spicyneuron
- SRA-RiskGate-4B↗
sriram1983007
**SRA-RiskGate-4B checks a stablecoin payment before an AI agent sends it, and answers `approve`, `hold` or `reject`** with reason codes. It is a 4B model, fine-tuned from `Qwen/Qwen3-4B-Instruct-2507`, that runs on a laptop. It reads three things: your policy, the payment request exactly as received (treated as untrusted), and the results of your own verification tools (signature checks, attestations, sanctions screening). It is a decision-support layer that sits **behind** deterministic checks, not a standalone security control. It also proposes settlement-aware remedies for payment disputes. All 4 unsafe approvals were prompt injections; the companion SDK's deterministic claims check holds all 4 (details and caveats below). The data is synthetic and no third party has reproduced these results yet.