AMD
Architecture
CDNA 4 powers the next-generation Instinct MI325X and MI350X accelerators. Built on TSMC 3nm with up to 288 GB HBM3e memory and native FP4 support for maximum inference density.
AI Relevance
With up to 288 GB HBM3e and FP4 support, CDNA 4 targets the highest-density AI inference deployments. Directly competes with NVIDIA Blackwell B200 for large-scale model serving.
Agentic Coding
CThis model is still usable for agentic-coding, but it is not the most specialized pick. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, lm-studio.
Chat
BThis model is a direct match for chat. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, lm-studio.
Coding
CThis model is a direct match for coding. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, lm-studio.
RAG
CThis model is a direct match for rag. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
Reasoning
BThis model is a direct match for reasoning. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, lm-studio.
Qwen 3 235B A22B
Llama 4 Maverick 17B 128E
Mixtral 8x22BDevstral 2 123B Instruct
Command A 111B
Qwen3.5 122B A10BMistral Small 4 119BQwen 2.5 72BQwen 2.5 VL 72BLlama 3.3 70BQwen3-Coder-NextQwen3.5 35B A3BQwen 2.5 Coder 32BQwen3.5 27BQwen3-Coder 30B A3B Instructgemma 3 27b itQwen3-VL 30B A3B InstructDevstral Small 2 24B InstructDevstral Small 1.1Codestral 2 25.08Qwen3.5 9BDeepSeek R1 0528 Qwen3 8BQwen3.5 4B
gemma 2bQwen2.5 3B InstructQwen2.5 1.5B InstructQwen3-Coder 480B A35B InstructQwen3.5 397B A17B
DeepSeek R1 671B
GLM-5
Kimi K2.5Mistral Large 3DeepSeek V3 671BJust out of reach
High-quality models that need a bit more memory
