Configure a rig →
NVIDIADatacenterAmpere DC

NVIDIA A100 40GB for local AI

NVIDIA A100 40GB provides 40 GB of VRAM for local AI. In the LocalIA catalog, 208 out of 242 models run comfortably on a single card.

View all compatible models →Rig around the 40GB ↗
VRAM
40GB
Category
Datacenter
Series
Ampere DC
Vendor
NVIDIA

Models that run comfortably

These models fit in 40 GB with room for context and stable inference.

★Mixtral 8x7Bmistral29.5 GBcomfortableQ4 · / 40 GB
Falcon 40Bfalcon30.7 GBcomfortableQ5 · / 40 GB
Command R 35Bcommand26.9 GBcomfortableQ5 · / 40 GB
Aya 23 35Baya26.9 GBcomfortableQ5 · / 40 GB
CodeLlama 34Bcodellama26.1 GBcomfortableQ5 · / 40 GB
Yi 1.5 34Byi26.1 GBcomfortableQ5 · / 40 GB
★dolphin 2.9.1 yi 1.5 34byi26.1 GBcomfortableQ5 · / 40 GB
★Qwen 2.5 32Bqwen24.6 GBcomfortableQ5 · / 40 GB
★Qwen 2.5 Coder 32Bqwen24.6 GBcomfortableQ5 · / 40 GB
★Qwen 3 32Bqwen24.6 GBcomfortableQ5 · / 40 GB
★QwQ 32Bqwq24.6 GBcomfortableQ5 · / 40 GB
★DeepSeek R1 Distill 32Bdeepseek24.6 GBcomfortableQ5 · / 40 GB
Qwen 2.5 VL 32Bqwen24.6 GBcomfortableQ5 · / 40 GB
★Granite 4 H-Small 32B-A9Bgranite24.6 GBcomfortableQ5 · / 40 GB
GLM-4.6glm24.6 GBcomfortableQ5 · / 40 GB
★GLM-4.7glm24.6 GBcomfortableQ5 · / 40 GB
★GLM-5glm24.6 GBcomfortableQ5 · / 40 GB
★GLM-5.1glm24.6 GBcomfortableQ5 · / 40 GB
★Qwen3 32Bqwen24.6 GBcomfortableQ5 · / 40 GB
★Qwen2.5 Coder 32B Instructqwen24.6 GBcomfortableQ5 · / 40 GB
★DeepSeek R1 Distill Qwen 32Bqwen24.6 GBcomfortableQ5 · / 40 GB
★Qwen2.5 32B Instructqwen24.6 GBcomfortableQ5 · / 40 GB
★Gemma 4 31Bgemma23.8 GBcomfortableQ5 · / 40 GB
★Qwen 3 30B A3Bqwen33.5 GBcomfortableQ8 · / 40 GB
MPT 30Bmpt33.5 GBcomfortableQ8 · / 40 GB
★Qwen3 Coder 30B A3B Instructqwen33.5 GBcomfortableQ8 · / 40 GB
★Qwen3 30B A3Bqwen33.5 GBcomfortableQ8 · / 40 GB
★Qwen3 30B A3B Instruct 2507qwen33.5 GBcomfortableQ8 · / 40 GB
★NVIDIA Nemotron 3 Nano 30B A3B BF16nemotron33.5 GBcomfortableQ8 · / 40 GB
★Gemma 2 27Bgemma30.2 GBcomfortableQ8 · / 40 GB

Unlocked in a 2x rig

With two cards in parallel (80 GB total), larger models become reachable.

★Mistral Large 123Bmistral77.3 GBtightQ4 · / 80 GB
★NVIDIA Nemotron 3 Super 120B A12B BF16nemotron75.4 GBtightQ4 · / 80 GB
★Llama 4 Scout 17Bx16llama68.5 GBtightQ4 · / 80 GB
★Command R+ 104Bcommand65.4 GBcomfortableQ4 · / 80 GB
★Qwen3 Next 80B A3B Instructqwen61.5 GBcomfortableQ5 · / 80 GB
★Qwen 2.5 72Bqwen55.3 GBcomfortableQ5 · / 80 GB
Qwen 2.5 VL 72Bqwen55.3 GBcomfortableQ5 · / 80 GB
★Qwen2.5 72B Instructqwen55.3 GBcomfortableQ5 · / 80 GB
Llama 2 70Bllama53.8 GBcomfortableQ5 · / 80 GB
Llama 3 70Bllama53.8 GBcomfortableQ5 · / 80 GB
Llama 3.1 70Bllama53.8 GBcomfortableQ5 · / 80 GB
★Llama 3.3 70Bllama53.8 GBcomfortableQ5 · / 80 GB
CodeLlama 70Bcodellama53.8 GBcomfortableQ5 · / 80 GB
★DeepSeek R1 Distill 70Bdeepseek53.8 GBcomfortableQ5 · / 80 GB
Hermes 3 70Bhermes53.8 GBcomfortableQ5 · / 80 GB

Unlocked in a 4x rig

Server-style configuration (160 GB total) for the largest open-weight models.

DeepSeek V2deepseek148.4 GBtightQ4 · / 160 GB
DeepSeek Coder V2deepseek148.4 GBtightQ4 · / 160 GB
★Qwen 3 235B A22Bqwen147.7 GBtightQ4 · / 160 GB
★Qwen3 235B A22Bqwen147.7 GBtightQ4 · / 160 GB
Falcon 180Bfalcon113.2 GBcomfortableQ4 · / 160 GB
Mixtral 8x22Bmistral108.3 GBcomfortableQ5 · / 160 GB

Similar GPUs

VRAM estimates updated 2026-05-12.