LLM EXPLORER 58,608 MODELS INDEXED

JiRackUltra 32B by CMSManhattan

By CMSManhattan · 3915 downloads
HF Repo ↗ Copy URL

JiRackUltra 32B is an open-source language model by CMSManhattan. Features: 32b LLM, VRAM: 12.3GB, Context: 128K, License: other, Quantized, LLM Explorer Score: 0.32.

  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 Parameters and Internals

LLM NameJiRackUltra 32b
Repository 🤗https://huggingface.co/CMSManhattan/JiRackUltra_32b 
Model Size32b
Required VRAM12.3 GB
Updated2026-08-17
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 GB1375
QwQ 32B GGUF32K / 7.7 GB381986
WPAIGPT Fse Patterns 132K / 65.8 GB1113
...Logic Mix 3 32B Mlx OptiQ 5bit128K / 22.3 GB411
...pSeek R1 Distill Qwen 32B 4bit128K / 18.5 GB779551
Hydraulic Deepseek 16bit128K / 65.8 GB520
...k R1 Distill Qwen 32B Bnb 4bit128K / 19.2 GB271729
...till Qwen 32B Abliterated 4bit128K / 18.5 GB8887
QwQ 32B Unsloth Bnb 4bit128K / 22.5 GB17947
...ogito V1 Preview Qwen 32B 4bit128K / 18.5 GB435