Qwen/Qwen3-30B-A3B-Base
31 derivatives checked
- Qwen/Qwen3-30B-A3B: Full fine-tune
- Mungert/Qwen3-30B-A6B-16-Extreme-GGUF: Full fine-tune
- Mungert/Qwen3-30B-A3B-GGUF: Full fine-tune
- Mungert/Qwen3-30B-A1.5B-High-Speed-GGUF: Full fine-tune
- Mungert/Pantheon-Proto-RP-1.8-30B-A3B-GGUF: Partial fine-tune
- unsloth/Qwen3-30B-A3B-Base: Same weights, repacked
- mradermacher/Qwen3-30B-A3B-Base-GGUF: Quantization
- mradermacher/Qwen3-30B-A3B-Base-i1-GGUF: Quantization
- zjiayu064/Qwen3-30B-A3B-Base-BitsMoE-2bit: Quantization
- ibnsina-llm/ibnsina-30b: Full fine-tune
- sartajbhuvaji/bonsai-qwen3-30b-a3b-teacher-corrected: Full fine-tune
- DevQuasar/Qwen.Qwen3-30B-A3B-Base-GGUF: Same weights, converted
- hon9kon9ize/CantoneseLLM-v2.0-30B-A3B-Thinking-Chat-Vector-Merged: Full fine-tune
- hon9kon9ize/CantoneseLLM-v2.0-30B-A3B-Thinking: Full fine-tune
- sartajbhuvaji/bonsai-qwen3-30b-a3b-teacher-corrected-lora: LoRA-style
- Aratako/Qwen3-30B-A3B-NSFW-JP: Full fine-tune
- DavidAU/Qwen3-30B-A6B-16-Extreme: Full fine-tune
- brandonmusic/Qwen3-30B-A3B-ShapleyMCG-K34-Validation-Reconstruction: LoRA-style
- Azure99/Blossom-V6.3-30B-A3B-GGUF: LoRA-style
- tokyotech-llm/Qwen3-Swallow-30B-A3B-CPT-v0.2: Full fine-tune
- DavidAU/Qwen3-30B-A1.5B-High-Speed: Full fine-tune
- unsloth/Qwen3-30B-A3B-Base-bnb-4bit: Quantization
- Antigma/Qwen3-30B-A3B-Base-GGUF: Quantization
- NePe/Qwen3-30B-A3B-GPTQ: Quantization
- Gryphe/Pantheon-Proto-RP-1.8-30B-A3B: Full fine-tune
- MegaScience/Qwen3-30B-A3B-MegaScience: Full fine-tune
- Rorical/qode-30b: Full fine-tune
- YOYO-AI/Qwen3-30B-A3B-YOYO-V2: Full fine-tune
- ar0cket1/qwen3-30b-a3b-base-reasoning-sft-nemotron-math-v4-500m: Full fine-tune
- Columbidae/Qwen3-16B-A3B-Base: LoRA-style (fewer layers)
2 other repos hold byte-for-byte identical weight files.