rafw007

qwen35-claude-coder

Qwen3.5 Claude Coder — local coding agents A family of custom models built on **Qwen3.5**, tuned to act as **autonomous coding and administration agents**.

vision tools thinking 4b 9b

9,268 Pulls 2 Tags Updated 4 months ago

Qwen3.6-35B-A3B-mlx-claude-coder-abliterated

A custom model built on Qwen3.6-35B-A3B (abliterated), tuned to act as an autonomous coding and administration agent. It speaks the Anthropic-compatible API, so it drives Claude Code fully locally — your code never leaves your machine.

vision tools thinking

5,038 Pulls 1 Tag Updated 3 months ago

gemma4-e4b-claude-coder

Stronger Gemma 4 E4B coding agent for Claude Code, 64K context, native tool-calling, runs fully local on 16GB Apple Silicon.

vision tools thinking

5,033 Pulls 1 Tag Updated 4 months ago

qwen36-a3b-claude-coder

Qwen3.6-35B-A3B MoE coding agent for Claude Code / Codex / opencode, 64K context, native tool-calling, honest tool use, safety guardrails intact

vision tools thinking

4,068 Pulls 2 Tags Updated 4 months ago

ornith-claude-coder

A custom model built on **DeepReinforce Ornith-1.0-9B**, tuned as an **autonomous coding and automation agent**. It speaks the Anthropic-compatible API, so it drives **Claude Code**, **Codex** and **opencode** fully locally - your code never leaves your m

2,236 Pulls 1 Tag Updated 3 months ago

gemma4-e2b-claude-coder

Fast, lightweight Gemma 4 E2B coding agent for Claude Code, 64K context, native tool-calling, 100% GPU on 16GB Apple Silicon.

vision tools thinking

1,354 Pulls 1 Tag Updated 4 months ago

qwen3.8-27b-redteam

Verified configuration + measured results for abliterated (uncensored) Qwen3.8-27B running as an autonomous redteam/sysadmin agent, served via llama-swap. This card documents OUR tested configuration and results on live tasks

1,255 Pulls 1 Tag Updated 3 weeks ago

gemma4-26b-claude-coder

Niestandardowy model Gemma 4 26B (~25,8B parametrów), dostrojony do działania jako niezależny agent kodowania i administracji . Obsługuje API zgodne z Anthropic, dzięki czemu obsługuje Claude Code, Codex i Opencode

tools thinking

964 Pulls 1 Tag Updated 4 months ago

glm-4.7-flash-opencode

A family of custom models built on **GLM-4.7-Flash** (MoE, 30B total / 3B active), tuned to act as autonomous coding agents — **each variant targeting a specific harness**

tools thinking

839 Pulls 1 Tag Updated 4 months ago

qwen3-coder-next-80b-redteam

Validated runtime configuration + measured results for an abliterated (uncensored) Qwen3-Coder-Next 80B-A3B running as an agentic coding backend on CPU via ik_llama.cpp

663 Pulls 1 Tag Updated 2 weeks ago

deepseek-v4-flash-fast

DeepSeek-V4-Flash-Fast is a custom agent build based on DeepSeek-V4-Flash (Open Weights, Apache-2.0, MoE, ~285B total / ~20B active). Weights in low-bit quantization for fully CPU-only deployment:

516 Pulls 1 Tag Updated 2 months ago

gemma4-e4b-claude-coder-admin

Gemma 4 E4B admin and devops agent for Claude Code, 32K context fully on GPU for stable throughput, native tool-calling, runs local on 16GB Apple Silicon.

vision tools thinking

509 Pulls 1 Tag Updated 4 months ago

bielik-codex

A custom model built on Bielik-Minitron-7B v3.0 Instruct, tuned to act as an autonomous coding and administration agent. It speaks the Anthropic-compatible API, so it drives Claude Code and OpenCode fully locally — your code never leaves your machine.

tools

249 Pulls 1 Tag Updated 4 months ago

bielik-custom-ocr-vision

A custom merged model: the vision layers were borrowed from Mistral-3 and joined with Bielik-7B (SpeakLeash). The result is a compact multimodal model that reads text from images — printed pages, scans.

vision

103 Pulls 1 Tag Updated 3 months ago