RavenX CyberAgent Qwen3.6 35B A3B Opus 4.7 OpenMythos Pentester BugHunter RATH Mlx 4bit Msq is an open-source language model by mlx-community. Features: 35b LLM, VRAM: 21.6GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.
35b 4-bit 4bit Abliterated Agent Apple-silicon Autonomous-agent Base model:huihui-ai/huihui-qw... Base model:quantized:huihui-ai... Blue-team Bug-bounty Code-generation Conversational Cvss Cwe Cybersecurity En Mcp Mitre-att&ck Mlx Moe Nist Openmythos Owasp Pentest Pentesting Quantized Qwen3.6 Qwen3 5 moe Rath-protocol Ravenx Red-team Region:us Safetensors Security Sharded Tensorflow Tool-calling Uncensored Vision
Model Card on HF 🤗: https://huggingface.co/mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
RavenX CyberAgent Qwen3.6 35B A3B Opus 4.7 OpenMythos Pentester BugHunter RATH Mlx 4bit Msq Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
RavenX CyberAgent Qwen3.6 35B A3B Opus 4.7 OpenMythos Pentester BugHunter RATH Mlx 4bit Msq Parameters and Internals
| LLM Name | RavenX CyberAgent Qwen3.6 35B A3B Opus 4.7 OpenMythos Pentester BugHunter RATH Mlx 4bit Msq |
| Repository 🤗 | https://huggingface.co/mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq |
| Model Name | unsloth/Qwen3.6-35B-A3B |
| Base Model(s) | |
| Model Size | 35b |
| Required VRAM | 21.6 GB |
| Updated | 2026-07-19 |
| Maintainer | mlx-community |
| Model Type | qwen3_5_moe |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen3_5MoeForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|vision_pad|> |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to RavenX CyberAgent Qwen3.6 35B A3B Opus 4.7 OpenMythos Pentester BugHunter RATH Mlx 4bit Msq
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3.6 35B A3B OptiQ 4bit | 0K / 22.1 GB | 14730 | 44 |
| ... 4.7 Opus Abliterated Mlx 8bit | 0K / 37 GB | 8726 | 24 |
| Ornith 1.0 35B UD Q2 K XL MLX | 0K / 13.3 GB | 1514 | 0 |
| ...ugHunter RATH Mlx 4bit Mtp Msq | 0K / 22.5 GB | 871 | 2 |
| Qwen3.6 35B A3B 4bit DWQ | 0K / 20.7 GB | 4088 | 16 |
| ...B Abliterated Heretic MLX 4bit | 0K / 24.5 GB | 2831 | 18 |
| Qwen3.6 35B A3B UD Q4 K XL Mlx | 0K / 22.7 GB | 1566 | 9 |
| Qwen3.5 35B A3B OptiQ 4bit | 0K / 22.2 GB | 720 | 3 |
| Qwen3.6 35B A3B UD Q8 K XL Mlx | 0K / 38.2 GB | 668 | 7 |
| Qwen3.6 35B Rust.mlx | 0K / 37.1 GB | 567 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq .
Rank the RavenX CyberAgent Qwen3.6 35B A3B Opus 4.7 OpenMythos Pentester BugHunter RATH Mlx 4bit Msq Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 55235 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a