Qwen3.6 35B A3B PrismQuant 4.75bit Vllm is an open-source language model by rdtand. Features: 35b LLM, VRAM: 23.5GB, License: apache-2.0, LLM Explorer Score: 0.37.
8-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3... Compressed-tensors Conversational En Moe Mtp Multilingual Mxfp8 Nvfp4 Prismquant Quantized Qwen3.6 Qwen3 5 moe Region:us Safetensors Sharded Speculative-decoding Tensorflow Vllm
Model Card on HF 🤗: https://huggingface.co/rdtand/Qwen3.6-35B-A3B-PrismQuant-4.75bit-vllm
Qwen3.6 35B A3B PrismQuant 4.75bit Vllm 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)
Qwen3.6 35B A3B PrismQuant 4.75bit Vllm Parameters and Internals
| LLM Name | Qwen3.6 35B A3B PrismQuant 4.75bit Vllm |
| Repository 🤗 | https://huggingface.co/rdtand/Qwen3.6-35B-A3B-PrismQuant-4.75bit-vllm |
| Base Model(s) | |
| Model Size | 35b |
| Required VRAM | 23.5 GB |
| Updated | 2026-04-20 |
| Maintainer | rdtand |
| Model Type | qwen3_5_moe |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen3_5MoeForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Transformers Version | 4.57.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Errors | replace |
Best Alternatives to Qwen3.6 35B A3B PrismQuant 4.75bit Vllm
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3.6 35B A3B NVFP4 | 0K / 25.6 GB | 1223 | 4 |
| Qwen3.6 35B A3B ConfigI MLX | 0K / 15.7 GB | 1780 | 2 |
| ...n3.5 35B A3B Abliterated Mxfp4 | 0K / 18.5 GB | 3155 | 3 |
| Qwen3.6 35B A3B RAM 25GB MLX | 0K / 26.4 GB | 20 | 2 |
| Qwen3.6 35B Rust.mlx | 0K / 37.1 GB | 609 | 8 |
| Qwen3.6 35B A3B UD Q4 K XL Mlx | 0K / 22.7 GB | 704 | 5 |
| ...B Abliterated Heretic MLX 4bit | 0K / 23.6 GB | 436 | 4 |
| Qwen3.6 35B A3B UD Q8 K XL Mlx | 0K / 38.2 GB | 628 | 0 |
| Qwen3.5 35B A3B UD Q4 K XL Mlx | 0K / 22.9 GB | 1352 | 5 |
| Qwen3.6 35B A3B 4bit DWQ | 0K / 20.7 GB | 14 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than rdtand/Qwen3.6-35B-A3B-PrismQuant-4.75bit-vllm .
Rank the Qwen3.6 35B A3B PrismQuant 4.75bit Vllm 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? 53053 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