Tag

Gemma4-12B v2 — Coding + Agentic Edition (GGUF)

A local, quantized Gemma 4 12B fine-tune packaged as GGUF quants that runs on ~4.5 GB VRAM. Optimized for coding and multi-step agentic tool use (read→reason→act→verify), ships multiple quant sizes (Q3_K_M–Q8_0) and MTP draft support; English-centric with trade-offs versus generalist models.

AFTER

Benchmark for evaluating procedural skill evolution in LLM agents: isolates reusable skill bodies, role-specific work surfaces, and hidden oracle assets to measure whether skill refinements transfer across tasks, roles, and model backbones. Includes 382 workplace tasks, 22 skills, and a controlled evaluation protocol.

Qwythos-9B-Claude-Mythos-5-1M-GGUF

Provides GGUF-quantized weights and runtime assets for running the Qwythos-9B reasoning LLM locally via llama.cpp and compatible runtimes. Key features include 1,048,576-token YaRN long-context, native function-calling, multimodal image input (requires mmproj), and multiple quantization/MTP variants tuned for different size/quality tradeoffs.

GLM-5.2 Agent traces

Provides 319 newline-delimited JSON agent session traces captured from GLM-5.2 using Teich for training agentic models. Preserves reasoning-first assistant fragments, tool-call events, and a dataset-level training-ready tool schema; convertible to OpenAI-style JSONL for SFT/distillation.

Laguna XS 2.1

A Mixture-of-Experts causal LLM (33B total, 3B active) tuned for agentic coding and long-horizon workflows; offers 262K-token context, mixed sliding-window/global attention, FP8 KV-cache and native preserved 'thinking' for tool-assisted agents, with local-ready quantized checkpoints.

Ornith-1.0-9B

A dense ~9B reasoning LLM optimized for agentic coding and tool-calling that emits explicit chain-of-thought (<think>) blocks and well-formed tool calls. Designed to run on a single 80GB GPU (~19GB bf16), uses self-scaffolding RL and exposes an OpenAI-compatible API.

Agents-A1: Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

35B Mixture-of-Experts agent model for long-horizon, multi-domain agent workflows; trained with a knowledge–action infrastructure that produces ~45K-token trajectories and supports native tool calling and function integration for research and deployment.

Qwen-AgentWorld-35B-A3B

Simulates agentic environments and predicts next environment states from actions and interaction history using a language-based world model across seven domains. Trained via a CPT→SFT→RL pipeline with an MoE architecture and very long context; intended for environment simulation and agent research.

AgentWorldBench

Provides 2,170 reference-grounded evaluation samples across seven agent domains (MCP, Search, Terminal, SWE, Android, Web, OS) to score language world models on Format, Factuality, Consistency, Realism and Quality. Includes per-domain JSONL files, judge prompts and an evaluation script for reproducible scoring.

EdgeBench

Measures how autonomous AI agents learn via long-horizon, feedback-rich executable tasks; publishes 51 public tasks from a 134-task suite and provides SForge, a two-container evaluation harness for iterative 12+ hour runs to track learning trajectories.

Ornith-1.0-9B-GGUF

Provides a GGUF-quantized local build of Ornith-1.0's 9B dense model for offline inference and terminal-focused coding agents. Supports OpenAI-compatible tool-calling, a 256K context window, and runs via llama.cpp or Ollama on a single high-memory GPU.

Qwopus-3.6-35B-A3B-Coder-MTP-GGUF

Thinking-off fine-tune for coding-agent workflows that prioritizes fast next-step decisions, lower token usage and stable multi-turn tool calling. Highlights: MoE 35B base, MTP speculative decoding, SWE-bench 62.4% (300 cases). Best for local agent loops and automated debug cycles; requires disciplined harnessing and schema consistency.