Configure a rig →
NVIDIAConsumerGTX 10

GTX 1070 for local AI

GTX 1070 provides 8 GB of VRAM for local AI. In the LocalIA catalog, 146 out of 242 models run comfortably on a single card.

View all compatible models →Rig around the 1070 ↗
VRAM
8GB
Category
Consumer
Series
GTX 10
Vendor
NVIDIA

Models that run comfortably

These models fit in 8 GB with room for context and stable inference.

Solar 10.7Bsolar6.7 GBcomfortableQ4 · / 8 GB
Falcon 3 10Bfalcon6.3 GBcomfortableQ4 · / 8 GB
★Gemma 2 9Bgemma5.7 GBcomfortableQ4 · / 8 GB
Yi 1.5 9Byi5.7 GBcomfortableQ4 · / 8 GB
★Qwen 3.5 9Bqwen5.7 GBcomfortableQ4 · / 8 GB
★GLM-4 9Bglm5.7 GBcomfortableQ4 · / 8 GB
★GLM-4.7 Flashglm5.7 GBcomfortableQ4 · / 8 GB
GLM-4.1V 9B Thinkingglm5.7 GBcomfortableQ4 · / 8 GB
★NVIDIA Nemotron Nano 9Bnemotron5.7 GBcomfortableQ4 · / 8 GB
★gemma 2 9b itgemma5.7 GBcomfortableQ4 · / 8 GB
Llama 3 8Bllama6.1 GBcomfortableQ5 · / 8 GB
★Llama 3.1 8Bllama6.1 GBcomfortableQ5 · / 8 GB
Ministral 8Bmistral6.1 GBcomfortableQ5 · / 8 GB
★Qwen 3 8Bqwen6.1 GBcomfortableQ5 · / 8 GB
DeepSeek R1 Distill 8Bdeepseek6.1 GBcomfortableQ5 · / 8 GB
Aya 23 8Baya6.1 GBcomfortableQ5 · / 8 GB
Granite 3 8Bgranite6.1 GBcomfortableQ5 · / 8 GB
★Hermes 3 8Bhermes6.1 GBcomfortableQ5 · / 8 GB
★DeepSeek R1 Distill Llama 8Bdeepseek6.1 GBcomfortableQ5 · / 8 GB
★MiniCPM 4.1 8Bminicpm6.1 GBcomfortableQ5 · / 8 GB
★Qwen3 8Bqwen6.1 GBcomfortableQ5 · / 8 GB
★Llama 3.1 8B Instructllama6.1 GBcomfortableQ5 · / 8 GB
★Meta Llama 3 8Bllama6.1 GBcomfortableQ5 · / 8 GB
★Meta Llama 3 8B Instructllama6.1 GBcomfortableQ5 · / 8 GB
★Llama 3.1 8Bllama6.1 GBcomfortableQ5 · / 8 GB
★DeepSeek R1 Distill Llama 8Bllama6.1 GBcomfortableQ5 · / 8 GB
★Llama 3.1 8B Instructllama6.1 GBcomfortableQ5 · / 8 GB
★Qwen3 8B Baseqwen6.1 GBcomfortableQ5 · / 8 GB
★saiga_llama3_8bllama6.1 GBcomfortableQ5 · / 8 GB
★Meta Llama 3.1 8B Instructllama6.1 GBcomfortableQ5 · / 8 GB

Tight models

These models barely fit. They can run, but context and speed will be limited.

★Mistral Nemo 12Bmistral7.5 GBtightQ4 · / 8 GB
★Gemma 3 12Bgemma7.5 GBtightQ4 · / 8 GB
StableLM 2 12Bstable7.5 GBtightQ4 · / 8 GB

Unlocked in a 2x rig

With two cards in parallel (16 GB total), larger models become reachable.

★Mistral Small 3 24Bmistral15.1 GBtightQ4 · / 16 GB
★Mistral Small 3.1 24Bmistral15.1 GBtightQ4 · / 16 GB
★Mistral Small 3.2 24Bmistral15.1 GBtightQ4 · / 16 GB
★Devstral Small 2 24Bdevstral15.1 GBtightQ4 · / 16 GB
Mistral Small 22Bmistral13.8 GBtightQ4 · / 16 GB
★Codestral 22Bcodestral13.8 GBtightQ4 · / 16 GB
Reka Flash 3 21Breka13.2 GBcomfortableQ4 · / 16 GB
InternLM 2.5 20Binternlm12.6 GBcomfortableQ4 · / 16 GB
DeepSeek V2 Litedeepseek12.3 GBcomfortableQ5 · / 16 GB
DeepSeek Coder V2 Litedeepseek12.3 GBcomfortableQ5 · / 16 GB
StarCoder 2 15Bstarcoder11.5 GBcomfortableQ5 · / 16 GB
★Phi-4 Reasoning Vision 15Bphi11.5 GBcomfortableQ5 · / 16 GB
★Qwen 2.5 14Bqwen10.8 GBcomfortableQ5 · / 16 GB
Qwen 2.5 Coder 14Bqwen10.8 GBcomfortableQ5 · / 16 GB
★Qwen 3 14Bqwen10.8 GBcomfortableQ5 · / 16 GB

Unlocked in a 4x rig

Server-style configuration (32 GB total) for the largest open-weight models.

★Mixtral 8x7Bmistral29.5 GBtightQ4 · / 32 GB
Falcon 40Bfalcon25.1 GBcomfortableQ4 · / 32 GB
Command R 35Bcommand26.9 GBcomfortableQ5 · / 32 GB
Aya 23 35Baya26.9 GBcomfortableQ5 · / 32 GB
CodeLlama 34Bcodellama26.1 GBcomfortableQ5 · / 32 GB
Yi 1.5 34Byi26.1 GBcomfortableQ5 · / 32 GB
★dolphin 2.9.1 yi 1.5 34byi26.1 GBcomfortableQ5 · / 32 GB
★Qwen 2.5 32Bqwen24.6 GBcomfortableQ5 · / 32 GB
★Qwen 2.5 Coder 32Bqwen24.6 GBcomfortableQ5 · / 32 GB
★Qwen 3 32Bqwen24.6 GBcomfortableQ5 · / 32 GB

Similar GPUs

VRAM estimates updated 2026-05-12.