cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit
huggingface/cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit
22 indexed models
22 matching models
huggingface/cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit
vertexAI/publishers/hf-cyankiwi/models/gemma-4-31b-it-awq-8bit@001
vertexAI/publishers/hf-cyankiwi/models/gemma-4-31b-it-qat-awq-int4@001
azureFoundry/HuggingFace/cyankiwi-glm-4.7-flash-awq-4bit@1
`cyankiwi/GLM-4.7-Flash-AWQ-4bit` powered by vLLM - [Original Model Card](https://huggingface.co/cyankiwi/GLM-4.7-Flash-AWQ-4bit) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a request to th
vertexAI/publishers/hf-cyankiwi/models/kat-coder-v2.5-dev-awq-int4@001
vertexAI/publishers/hf-cyankiwi/models/laguna-s-2.1-awq-int4@001
vertexAI/publishers/hf-cyankiwi/models/minimax-m2.1-awq-4bit@001
vertexAI/publishers/hf-cyankiwi/models/minimax-m2.7-awq-4bit@001
vertexAI/publishers/hf-cyankiwi/models/qwen3-30b-a3b-instruct-2507-awq-4bit@001
azureFoundry/HuggingFace/cyankiwi-qwen3.5-122b-a10b-awq-4bit@1
`cyankiwi/Qwen3.5-122B-A10B-AWQ-4bit` powered by vLLM - [Original Model Card](https://huggingface.co/cyankiwi/Qwen3.5-122B-A10B-AWQ-4bit) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a reque
vertexAI/publishers/hf-cyankiwi/models/qwen3.6-27b-awq-bf16-int4@001
huggingface/cyankiwi/Qwen3.6-27B-AWQ-INT4
vertexAI/publishers/hf-cyankiwi/models/qwen3.6-35b-a3b-awq-4bit@001
vertexAI/publishers/hf-cyankiwi/models/qwen3.6-35b-a3b-awq-nvfp4@001
vertexAI/publishers/hf-cyankiwi/models/qwen3.8-27b-awq-bf16-int4@001
vertexAI/publishers/hf-cyankiwi/models/qwen3.8-27b-awq-fp8@001
huggingface/cyankiwi/Qwen3.8-27B-AWQ-INT4
huggingface/cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.