LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Leaderboards   Agents   Benchmarks    LLM Hosting    Advertise

JiRackUltra 32B by CMSManhattan

 »  All LLMs  »  CMSManhattan  »  JiRackUltra 32B   URL Share it on

  2011   

JiRackUltra 32B is an open-source language model by CMSManhattan. Features: 32b LLM, VRAM: 12.3GB, Context: 128K, License: other, Quantized, LLM Explorer Score: 0.34.

  1.58bit   Ar   Bitnet   Conversational   Cpu   De   Deepseek   Deepseek-r1   Efficient   En   Endpoints compatible   Es   Fr   Gguf   It   Ja   Jirack   Ko   Low-memory   Pt   Q2   Quantized   Qwen2   Qwen2.5   Region:us   Robotics   Routing   Ru   Safetensors   Ternary   Th   Tool-call   Vi   Web-ui   Zh
Model Card on HF 🤗: https://huggingface.co/CMSManhattan/JiRackUltra_32b 

JiRackUltra 32b Benchmarks

LLME Score: 0.33943
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
JiRackUltra 32B (CMSManhattan/JiRackUltra_32b)

JiRackUltra 32B Parameters and Internals

LLM NameJiRackUltra 32b
Repository 🤗https://huggingface.co/CMSManhattan/JiRackUltra_32b 
Model Size32b
Required VRAM12.3 GB
Updated2026-08-04
MaintainerCMSManhattan
Model Typeqwen2
Model Files  65.5 GB   12.3 GB   15.9 GB   19.9 GB   65.5 GB   65.5 GB
Supported Languagesen zh ja ko fr es pt de it ru ar vi th
GGUF QuantizationYes
Quantization Typeq2|gguf|q4_k
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Tokenizer ClassQwen2Tokenizer
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to JiRackUltra 32B

Best Alternatives
Context / RAM
Downloads
Likes
QwentileSwap32K / 65 GB485
QwQ 32B GGUF32K / 7.7 GB381986
WPAIGPT Fse Patterns 132K / 65.8 GB1113
...pSeek R1 Distill Qwen 32B 4bit128K / 18.5 GB720651
Hydraulic Deepseek 16bit128K / 65.8 GB520
...k R1 Distill Qwen 32B Bnb 4bit128K / 19.2 GB271729
...till Qwen 32B Abliterated 4bit128K / 18.5 GB6636
...ogito V1 Preview Qwen 32B 4bit128K / 18.5 GB715
...T1 Flash Lightest 32B Mlx 4Bit128K / 18.5 GB2318
QwQ 32B Unsloth Bnb 4bit128K / 22.5 GB12047

Rank the JiRackUltra 32B 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 55613 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer