19 models
CodeQwen1.5-7B-Chat 官方优化版本
Wraith Coder 7B is a specialized code generation model fine-tuned from Qwen2.5-Coder-7B-Instruct. Wraith specializes in algorithmic reasoning, systems programming, and technical communication optimization.
https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-128K-GGUF
Qwen2.5-Coder-7B fine-tuned for uncensored code generation. Made by RACER IS OP.
Bob: senior PHP & Laravel assistant on Qwen2.5-Coder 7B. Detects Laravel 10–13 from your project, gives version-specific answers. Eloquent, APIs, queues, Sanctum, testing. Run: ollama run bhavingajjar/qwen2.5-7b-laravel-coder
A concise, root-cause-first coding assistant built on Qwen2.5-Coder 7B. Debug and generate code with zero filler — runs entirely locally via Ollama.
Lumen writes code, runs shell commands, uses git/GitHub, and fixes bugs autonomously. Fine-tuned on Qwen2.5-Coder-7B-Instruct with LoRA for tool-use and agentic workflows.
https://huggingface.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF
Code-safety abliterated build of Qwen/Qwen3.6-27B, refusals on malicious-code requests reduced via a *code-specific* refusal-direction ablation, while preserving coherence.
Enterprise coding & engineering assistant by GOCOSYS Technologies — built on Qwen2.5-Coder-7B. Great for PHP, Laravel, Python, JS/TS, React, Node, Docker & DevOps.
Qwen 2.5 Coder 7b Finetuned on MainframeBench for Cobol Coding
Qwen 3.8 27B, Distilled against Opus 5.5, GPT 6 Astra, and Grok 4.7
A custom model of Qwen2.5-coder:7B-Instruct with the Qwen2.5-coder:3B-instruct used as a speculative fill model to speed up inference. Primarily made for TabbyML Usage.
Model architecture qwen3next parameters 79.7B context length 262144 embedding length 2048 quantization Q4_K_M requires 0.15.5 Capabilities completion tools Parameters top
A 72B parameter coding model optimized for software engineering tasks, based on the Qwen2.5-72B architecture.
Instinct is Continue's state-of-the-art open Next Edit model. Robustly fine-tuned from Qwen2.5-Coder-7B, Instinct intelligently predicts your next move to keep you in flow.
LFM2-8B-A1B is the best on-device MoE in terms of both quality (comparable to 3-4B dense models) and speed (faster than Qwen3-1.7B). Updated LFM2.5-8B-A1B is now available!
NetIntelOCR model is fine tuned from Qwen2.5-VL-7B-Instruct to support Security and Network extraction for Semantic CMDBs.
Text + Vision Qwen3.8-27B-FableColdFusion-735882-HereticUncensored-NEOCODERMAX-MTP-NVFP4-Q8-Q3