LLM EXPLORER 59,598 MODELS INDEXED

GKA Primed HQwen3 32B Instruct by amazon

By amazon · 33 downloads
HF Repo ↗ Copy URL

GKA Primed HQwen3 32B Instruct is an open-source language model by amazon. Features: 32b LLM, VRAM: 69GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.23.

  Arxiv:2502.17605   Arxiv:2511.21016 Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-32b   Conversational   Endpoints compatible   Gated-kalmanet   Hybrid   Hybrid qwen3   Instruct   Instruction-tuned   Linear-attention   Long-context   Priming   Region:us   Safetensors   Sharded   Ssm   State-space-model   Tensorflow
Model Card on HF 🤗: https://huggingface.co/amazon/GKA-primed-HQwen3-32B-Instruct 

GKA Primed HQwen3 32B Instruct Parameters and Internals

LLM NameGKA Primed HQwen3 32B Instruct
Repository 🤗https://huggingface.co/amazon/GKA-primed-HQwen3-32B-Instruct 
Base Model(s)  Qwen3 32B   Qwen/Qwen3-32B
Model Size32b
Required VRAM69 GB
Updated2026-08-02
Maintaineramazon
Model Typehybrid_qwen3
Instruction-BasedYes
Model Files  4.8 GB: 1-of-15   4.8 GB: 2-of-15   4.8 GB: 3-of-15   5.0 GB: 4-of-15   4.9 GB: 5-of-15   4.7 GB: 6-of-15   5.0 GB: 7-of-15   5.0 GB: 8-of-15   5.0 GB: 9-of-15   4.9 GB: 10-of-15   4.9 GB: 11-of-15   4.9 GB: 12-of-15   4.8 GB: 13-of-15   3.9 GB: 14-of-15   1.6 GB: 15-of-15
Model ArchitectureHybridQwen3ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version5.3.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to GKA Primed HQwen3 32B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
GDN Primed HQwen3 32B Instruct128K / 68.9 GB93