LLM EXPLORER 65,121 MODELS INDEXED

Qwen3.5 2B M40 6bit by nikimori

By nikimori · 463 downloads
HF Repo ↗ Copy URL

Qwen3.5 2B M40 6bit is an open-source language model by nikimori. Features: 2b LLM, VRAM: 1.5GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  6-bit   6bit Base model:merge:qwen/qwen3.5-... Base model:merge:qwen/qwen3.5-...   Base model:qwen/qwen3.5-2b Base model:qwen/qwen3.5-2b-bas...   Conversational   Merge   Mlx   Quantized   Qwen3 5   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/nikimori/Qwen3.5-2B-M40-6bit 

Qwen3.5 2B M40 6bit Parameters and Internals

LLM NameQwen3.5 2B M40 6bit
Repository 🤗https://huggingface.co/nikimori/Qwen3.5-2B-M40-6bit 
Base Model(s)  Qwen/Qwen3.5-2B-Base   Qwen/Qwen3.5-2B   Qwen/Qwen3.5-2B-Base   Qwen/Qwen3.5-2B
Model Size2b
Required VRAM1.5 GB
Updated2026-10-21
Maintainernikimori
Model Typeqwen3_5
Model Files  1.5 GB
Quantization Type6bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 2B M40 6bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 2B Base 6bit0K / 1.5 GB4171
Qwen3.5 2B 4bit Slim0K / 1.1 GB2271
Loopl 2B 4bit0K / 1.7 GB1371
Qwen3.5 2B MLX 4bit0K / 1.7 GB123102
Qwen3.8 2B Distill Mlx 5Bit0K / 1.3 GB3871
Qwen3.5 2B 6bit0K / 2.2 GB86807
Mavery Geselle 2B MLX 4bit0K / 1.7 GB772
Qwen3.5 2B 4bit0K / 1.7 GB53745
Qwen3.5 2B OptiQ 4bit0K / 0.7 GB129612
Spartan 1.2 2B MLX 8bit0K / 1.1 GB270