NVIDIA
Architecture
Volta is NVIDIA's datacenter architecture that introduced the first Tensor Cores for mixed-precision matrix operations. The V100 was the dominant AI training GPU before Ampere, offering 32 GB HBM2 memory and NVLink 2.0.
AI Relevance
First-generation Tensor Cores provide FP16 mixed-precision acceleration. The V100's 32 GB HBM2 and high bandwidth (900 GB/s) still make it viable for running mid-sized models, though its age limits software compatibility with newer frameworks.
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, ollama, 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, ollama, 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, ollama, lm-studio.
RAG
CThis model is a direct match for rag. It sits in the middle of the current model mix. It fits natively with comfortable headroom.
Reasoning
CThis 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, ollama, lm-studio.
Qwen3-VL 30B A3B InstructQwen3-Coder 30B A3B Instruct
Devstral Small 2 24B InstructDevstral Small 1.1
Qwen3.5 27Bgemma 3 27b itCodestral 2 25.08Qwen 2.5 Coder 32BQwen3.5 35B A3BQwen3.5 9BDeepSeek R1 0528 Qwen3 8BQwen3.5 4BQwen2.5 3B Instruct
gemma 2bQwen2.5 1.5B Instruct
DeepSeek R1 671BDevstral 2 123B Instruct
GLM-5
Kimi K2.5Mistral Large 3Mistral Small 4 119BQwen3-Coder 480B A35B InstructQwen3-Coder-NextQwen3.5 122B A10BDeepSeek V3 671BMixtral 8x22BQwen 2.5 72BQwen 3 235B A22BQwen3.5 397B A17B
Llama 3.3 70BLlama 4 Maverick 17B 128E
Command A 111BQwen 2.5 VL 72BJust out of reach
High-quality models that need a bit more memory
Upgrade paths
See what you unlock with more powerful hardware
Upgrade options
NVIDIA A100 40GBNext step up~$10,000 MSRP
RTX A6000 48GBNVIDIA upgrade~$4,650 MSRP
~$2,499 MSRP
~$8,000 MSRP
