LLM EXPLORER 58,133 MODELS INDEXED

Qwen35 4B T13 Opd Rkl Ckpt50 by aziz9788

By aziz9788 · 467 downloads
HF Repo ↗ Copy URL

Qwen35 4B T13 Opd Rkl Ckpt50 is an open-source language model by aziz9788. Features: 4b LLM, VRAM: 8.4GB, Context: 256K, License: apache-2.0, Merged, LLM Explorer Score: 0.31.

  Merged Model   Ar   Arabic   Conversational   En   Endpoints compatible   Opd   Qwen   Qwen3 5 text   Region:us   Reverse-kl   Rkl   Safetensors   T13
Model Card on HF 🤗: https://huggingface.co/aziz9788/qwen35-4b-t13-opd-rkl-ckpt50 

Qwen35 4B T13 Opd Rkl Ckpt50 Parameters and Internals

LLM NameQwen35 4B T13 Opd Rkl Ckpt50
Repository 🤗https://huggingface.co/aziz9788/qwen35-4b-t13-opd-rkl-ckpt50 
Base Model(s)  merged_t13_ckpt12   /merged_t13_ckpt12
Merged ModelYes
Model Size4b
Required VRAM8.4 GB
Updated2026-08-11
Maintaineraziz9788
Model Typeqwen3_5_text
Model Files  8.4 GB
Supported Languagesar en
Model ArchitectureQwen3_5ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size248320
Errorsreplace

Best Alternatives to Qwen35 4B T13 Opd Rkl Ckpt50

Best Alternatives
Context / RAM
Downloads
Likes
Agents A1 4B Fable Preview256K / 8.4 GB1030
...ts A1 4B Fable Preview Heretic256K / 8.4 GB22852
Zira Researcher256K / 8.4 GB1140412
...nts A1 4B Kimi Preview Heretic256K / 8.4 GB2870
Qwen3.5 4B EU256K / 9.7 GB870
Qwen3.5 4B INT8256K / 4.8 GB2052
Qwen35 4B Soyuz Merged256K / 8.4 GB733
Retrico Lm 4B Finetuned V4256K / 0 GB1430
Holo 3.1 4B Coder256K / 16.8 GB411
Qwen3.5 4B INT8256K / 4.8 GB1112
Note: green Score (e.g. "73.2") means that the model is better than aziz9788/qwen35-4b-t13-opd-rkl-ckpt50.