LLM EXPLORER 56,604 MODELS INDEXED

Lacaille MoT 4B Supreme2 by prithivMLmods

By prithivMLmods · 15 downloads
HF Repo ↗ Copy URL

Lacaille MoT 4B Supreme2 is an open-source language model by prithivMLmods. Features: 4b LLM, VRAM: 8.1GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.18.

  Arxiv:2309.00071   Arxiv:2412.15115 Base model:finetune:prithivmlm... Base model:prithivmlmods/qwen3...   Code   Conversational Dataset:nvidia/opencodereasoni... Dataset:open-r1/mixture-of-tho...   En   Endpoints compatible   Math   Mixture-of-thoughts   Mot   Qwen3   Reasoning   Region:us   Safetensors   Science   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/prithivMLmods/Lacaille-MoT-4B-Supreme2 

Lacaille MoT 4B Supreme2 Parameters and Internals

LLM NameLacaille MoT 4B Supreme2
Repository 🤗https://huggingface.co/prithivMLmods/Lacaille-MoT-4B-Supreme2 
Base Model(s)  Qwen3 4B Ft Bf16   prithivMLmods/Qwen3-4B-ft-bf16
Model Size4b
Required VRAM8.1 GB
Updated2026-08-06
MaintainerprithivMLmods
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Lacaille MoT 4B Supreme2

Best Alternatives
Context / RAM
Downloads
Likes
Fable Traces256K / 8.1 GB5530209
FastContext 1.0 4B SFT256K / 8.1 GB5735357
Qwen3 4B Instruct 2507256K / 8.1 GB3109972911
GRPO 4 70256K / 8.1 GB50
Lightning 4B256K / 8.1 GB136
FastContext 1.0 4B RL256K / 8.1 GB455961
Qwen3 4B Thinking 2507256K / 8.1 GB291023606
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB110074478
Typhoon2.5 Qwen3 4B256K / 8 GB4898776
Neuron 4B Instruct256K / 8.1 GB3131
Note: green Score (e.g. "73.2") means that the model is better than prithivMLmods/Lacaille-MoT-4B-Supreme2.