Configure a rig →
AMDDatacenterInstinct CDNA 1-2

Instinct MI210 for local AI

Instinct MI210 provides 64 GB of VRAM for local AI. In the LocalIA catalog, 223 out of 242 models run comfortably on a single card.

View all compatible models →Rig around the MI210 ↗
VRAM
64GB
Category
Datacenter
Series
Instinct CDNA 1-2
Vendor
AMD

Models that run comfortably

These models fit in 64 GB with room for context and stable inference.

★Qwen3 Next 80B A3B Instructqwen50.3 GBcomfortableQ4 · / 64 GB
★Qwen 2.5 72Bqwen45.3 GBcomfortableQ4 · / 64 GB
Qwen 2.5 VL 72Bqwen45.3 GBcomfortableQ4 · / 64 GB
★Qwen2.5 72B Instructqwen45.3 GBcomfortableQ4 · / 64 GB
Llama 2 70Bllama53.8 GBcomfortableQ5 · / 64 GB
Llama 3 70Bllama53.8 GBcomfortableQ5 · / 64 GB
Llama 3.1 70Bllama53.8 GBcomfortableQ5 · / 64 GB
★Llama 3.3 70Bllama53.8 GBcomfortableQ5 · / 64 GB
CodeLlama 70Bcodellama53.8 GBcomfortableQ5 · / 64 GB
★DeepSeek R1 Distill 70Bdeepseek53.8 GBcomfortableQ5 · / 64 GB
Hermes 3 70Bhermes53.8 GBcomfortableQ5 · / 64 GB
★Llama 3.1 Nemotron 70Bnemotron53.8 GBcomfortableQ5 · / 64 GB
Athene 70Bathene53.8 GBcomfortableQ5 · / 64 GB
★Llama 3.3 70B Instructllama53.8 GBcomfortableQ5 · / 64 GB
★Llama 3.1 70B Instructllama53.8 GBcomfortableQ5 · / 64 GB
★Mixtral 8x7Bmistral52.5 GBcomfortableQ8 · / 64 GB
Falcon 40Bfalcon44.7 GBcomfortableQ8 · / 64 GB
Command R 35Bcommand39.1 GBcomfortableQ8 · / 64 GB
Aya 23 35Baya39.1 GBcomfortableQ8 · / 64 GB
CodeLlama 34Bcodellama38.0 GBcomfortableQ8 · / 64 GB
Yi 1.5 34Byi38.0 GBcomfortableQ8 · / 64 GB
★dolphin 2.9.1 yi 1.5 34byi38.0 GBcomfortableQ8 · / 64 GB
★Qwen 2.5 32Bqwen35.8 GBcomfortableQ8 · / 64 GB
★Qwen 2.5 Coder 32Bqwen35.8 GBcomfortableQ8 · / 64 GB
★Qwen 3 32Bqwen35.8 GBcomfortableQ8 · / 64 GB
★QwQ 32Bqwq35.8 GBcomfortableQ8 · / 64 GB
★DeepSeek R1 Distill 32Bdeepseek35.8 GBcomfortableQ8 · / 64 GB
Qwen 2.5 VL 32Bqwen35.8 GBcomfortableQ8 · / 64 GB
★Granite 4 H-Small 32B-A9Bgranite35.8 GBcomfortableQ8 · / 64 GB
GLM-4.6glm35.8 GBcomfortableQ8 · / 64 GB

Unlocked in a 2x rig

With two cards in parallel (128 GB total), larger models become reachable.

Falcon 180Bfalcon113.2 GBtightQ4 · / 128 GB
Mixtral 8x22Bmistral108.3 GBcomfortableQ5 · / 128 GB
★Mistral Large 123Bmistral94.5 GBcomfortableQ5 · / 128 GB
★NVIDIA Nemotron 3 Super 120B A12B BF16nemotron92.2 GBcomfortableQ5 · / 128 GB
★Llama 4 Scout 17Bx16llama83.7 GBcomfortableQ5 · / 128 GB
★Command R+ 104Bcommand79.9 GBcomfortableQ5 · / 128 GB

Unlocked in a 4x rig

Server-style configuration (256 GB total) for the largest open-weight models.

★Llama 3.1 405Bllama254.6 GBtightQ4 · / 256 GB
Hermes 3 405Bhermes254.6 GBtightQ4 · / 256 GB
★Llama 4 Maverick 17Bx128llama251.5 GBtightQ4 · / 256 GB
Nemotron 340Bnemotron213.7 GBcomfortableQ4 · / 256 GB
DeepSeek V2deepseek181.3 GBcomfortableQ5 · / 256 GB
DeepSeek Coder V2deepseek181.3 GBcomfortableQ5 · / 256 GB
★Qwen 3 235B A22Bqwen180.6 GBcomfortableQ5 · / 256 GB
★Qwen3 235B A22Bqwen180.6 GBcomfortableQ5 · / 256 GB

Similar GPUs

VRAM estimates updated 2026-05-12.