Models

fahisshehandim/Neuris-Apex

Neuris APEX is a 3B cybersecurity input-classification model fine-tuned from Ministral 3B to identify malicious, suspicious, ambiguous, and safe user-controlled inputs across common attack families.

mistral-large-4

Mistral Large 4 is Mistral's open-weight, general-purpose multimodal model. Its granular Mixture-of-Experts design activates 52B of 1.05T total parameters, with a 1.6B vision encoder handling images.

siddhu19/swift-15

Compact, mixed-precision GGUF quantizations of Swift 1.5 Qwen3.8-27B, with Swift-specific refinement using the per-tensor allocations from ISTA-DASLab's GSQ-RCO release.

hisparshmishra1/claude-code-3b

Fine-tuned 3B coding specialist optimized for Claude Code CLI and agentic tool use. Runs 100% locally in NVIDIA GPU VRAM (GTX 1650 4GB compatible).

dungeonlabit/jarvis-mistral

richardyoung/phi-4-mini-instruct-heretic

Uncensored Phi-4-mini-instruct via Heretic: 5/100 refusals (from 99), KL 0.038. 3.8B with 128K context, MIT.

richardyoung/lfm2.5-1.2b-instruct-heretic

Uncensored LFM2.5-1.2B-Instruct via Heretic: 3/100 refusals (from 98), KL 0.059. Tiny and fast; runs on almost anything.

vegeta/ministral3-14b-reasoning

vegeta/ministral3-8b-reasoning

optimistic_mcnulty_933/mistral-loop

Mistral LOOP 7B is a lightweight Mistral 7B model with a behavioral prompt layer for structured self-checking, requirement tracking, and answer refinement.

michaelmontuori/Qwen2.5-7B-Instruct-GGUF

Initially built this 7b model to fit in my RTX 4060 with 8GB

beeble/ministral-3-3b-instruct-2512-fb16

The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. This version is the converted model from Huggingface with full FB16 precision.

mvincig11/ministral-3-3b-mlx

Ministral 3 3B Instruct, quantized to Q4_K_M for fast local Ollama inference on Apple Silicon.

optimistic_mcnulty_933/gpt-oss-loop-20b

GPT OSS 20B with the LOOP V2 behavioral prompt layer for structured self-checking, requirement tracking, and answer refinement. No weight changes or fine-tuning. A more accessible companion to the 120B version.

optimistic_mcnulty_933/gpt-oss-loop-120b

GPT OSS 120B with the LOOP V2 behavioral prompt layer for structured self‑checking, requirement tracking, and answer refinement. No weight changes or fine‑tuning.

onnyx/Prism

PRISM: Predictive Retrieval and Inference of Spectral Molecules A hybrid, retrieval-augmented deep learning framework for translating LC-MS/MS spectra into chemically valid 2D structures (SMILES/SELFIES) for both known and novel compounds.

frob/mistral-small-4

virtuanista/lfm2.5-8b-a1b-uncensored

Versión GGUF sin censura del modelo lfm2.5-8b-a1b de Liquid AI, lista para ejecutar en local.

jewelzufo/miniCPM5-1B-SP-Translate

Translates English inputs into Spanish. Experimental.

jessicalw34/TORUS

TORUS is a SnapKitty finance-focused language model fine-tuned for financial research and structured analysis. (Mistral 8B — orchestrator) temperature 0.1 top_k 30 top_p 0.9 num_ctx 8192,