LLM EXPLORER 66,845 MODELS INDEXED

Viper 9B by rrchat

By rrchat · 46 downloads
HF Repo ↗ Copy URL

Viper 9B is an open-source language model by rrchat. Features: 9b LLM, VRAM: 17.9GB, Context: 256K, License: other, Instruction-Based, LLM Explorer Score: 0.29.

  Agent Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-9b   Code   Conversational Dataset:m-a-p/codefeedback-fil... Dataset:nvidia/nemotron-sft-ag... Dataset:nvidia/opencodeinstruc... Dataset:nvidia/openmathinstruc... Dataset:open-r1/openr1-math-22... Dataset:vikhrmodels/grandmaste...   En   Endpoints compatible   Function-calling   Image-text-to-text   Instruct   Math   Qwen   Qwen3.5   Qwen3 5 text   Reasoning   Region:us   Rrchat   Ru   Russian   Safetensors   Sharded   Tensorflow   Tool-use   Unsloth   Viper
Model Card on HF 🤗: https://huggingface.co/rrchat/Viper-9B 

Viper 9B Parameters and Internals

LLM NameViper 9B
Repository 🤗https://huggingface.co/rrchat/Viper-9B 
Base Model(s)  Qwen/Qwen3.5-9B   Qwen/Qwen3.5-9B
Model Size9b
Required VRAM17.9 GB
Updated2026-11-06
Maintainerrrchat
Model Typeqwen3_5_text
Instruction-BasedYes
Model Files  2.0 GB: 1-of-5   4.0 GB: 2-of-5   4.0 GB: 3-of-5   4.0 GB: 4-of-5   3.9 GB: 5-of-5
Supported Languagesru en
Model ArchitectureQwen3_5ForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version5.17.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size248320
Errorsreplace

Best Alternatives to Viper 9B

Best Alternatives
Context / RAM
Downloads
Likes
NeoHorse 1 9B256K / 18 GB1250196
FlashModel Qwen3.5 9B256K / 17.9 GB3250
NeoHorse 1 9B FP8 Calibrated256K / 11 GB271
Mitra Qwen35 It256K / 17.9 GB452
Nyx RP 9B Instruct 2608 V1256K / 18.4 GB31675
Note: green Score (e.g. "73.2") means that the model is better than rrchat/Viper-9B.