Coding Models

150 profiles in this group. Use this hub page to compare practical VRAM floor, expected throughput, and best local-vs-cloud path.

Model Data VRAM min VRAM optimal Best local GPU Cloud fallback Detail
Qwen3 Coder 480B CLOUD Estimated 215GB 223GB Cloud-first (no practical single-GPU local) H100/H200 class Open
Qwen3 Coder 480B FP16 Estimated 225GB 237GB Cloud-first (no practical single-GPU local) H100/H200 class Open
Qwen3 Coder 480B Q4 Estimated 213GB 223GB Cloud-first (no practical single-GPU local) H100/H200 class Open
Qwen3 Coder 480B Q5 Estimated 215GB 225GB Cloud-first (no practical single-GPU local) H100/H200 class Open
Qwen3 Coder 480B Q8 Estimated 219GB 229GB Cloud-first (no practical single-GPU local) H100/H200 class Open
DeepSeek Coder V2 236B FP16 Estimated 150GB 162GB Cloud-first (no practical single-GPU local) H100/H200 class Open
DeepSeek Coder V2 236B Q4 Estimated 138GB 148GB Cloud-first (no practical single-GPU local) H100/H200 class Open
DeepSeek Coder V2 236B Q5 Estimated 140GB 150GB Cloud-first (no practical single-GPU local) H100/H200 class Open
DeepSeek Coder V2 236B Q8 Estimated 144GB 154GB Cloud-first (no practical single-GPU local) H100/H200 class Open
Qwen3 235B FP16 Estimated 150GB 162GB Cloud-first (no practical single-GPU local) H100/H200 class Open
Qwen3 235B Q4 Estimated 138GB 148GB Cloud-first (no practical single-GPU local) H100/H200 class Open
Qwen3 235B Q5 Estimated 140GB 150GB Cloud-first (no practical single-GPU local) H100/H200 class Open
Qwen3 235B Q8 Estimated 144GB 154GB Cloud-first (no practical single-GPU local) H100/H200 class Open
Qwen2.5 72B FP16 Estimated 50GB 62GB Dual RTX 4090 (model parallel) A100 80GB Open
Qwen2.5 72B Q4 Estimated 38GB 48GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 72B Q5 Estimated 40GB 50GB Dual RTX 4090 (model parallel) A100 80GB Open
Qwen2.5 72B Q8 Estimated 44GB 54GB Dual RTX 4090 (model parallel) A100 80GB Open
CodeLlama 70B FP16 Estimated 50GB 62GB Dual RTX 4090 (model parallel) A100 80GB Open
CodeLlama 70B Q4 Estimated 38GB 48GB RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 70B Q5 Estimated 40GB 50GB Dual RTX 4090 (model parallel) A100 80GB Open
CodeLlama 70B Q8 Estimated 44GB 54GB Dual RTX 4090 (model parallel) A100 80GB Open
CodeLlama 34B FP16 Estimated 30GB 42GB RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 34B Q4 Estimated 16GB 20GB RTX 3090 24GB A6000 48GB Open
CodeLlama 34B Q5 Estimated 20GB 22GB RTX 3090 24GB A6000 48GB Open
CodeLlama 34B Q8 Estimated 24GB 34GB RTX 6000 Ada 48GB A100 80GB Open
DeepSeek Coder 33B FP16 Estimated 30GB 42GB RTX 6000 Ada 48GB A100 80GB Open
DeepSeek Coder 33B Q4 Estimated 16GB 20GB RTX 3090 24GB A6000 48GB Open
DeepSeek Coder 33B Q5 Estimated 20GB 22GB RTX 3090 24GB A6000 48GB Open
DeepSeek Coder 33B Q8 Estimated 24GB 34GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 32B FP16 Estimated 30GB 42GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 32B Q4 Estimated 18GB 28GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 32B Q5 Estimated 20GB 30GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 32B Q8 Estimated 24GB 34GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 Coder 32B FP16 Estimated 30GB 42GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 Coder 32B Q4 Estimated 16GB 20GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 32B Q5 Estimated 20GB 22GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 32B Q8 Estimated 24GB 34GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 32B FP16 Estimated 30GB 42GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 32B Q4 Measured 18GB 28GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 32B Q5 Measured 20GB 30GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 32B Q8 Estimated 24GB 34GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 30B FP16 Estimated 30GB 42GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 30B Q4 Estimated 18GB 28GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 30B Q5 Estimated 20GB 30GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 30B Q8 Estimated 24GB 34GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 Coder 30B CLOUD Estimated 20GB 28GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 Coder 30B FP16 Estimated 30GB 42GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 Coder 30B Q4 Estimated 18GB 28GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 Coder 30B Q5 Estimated 20GB 30GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 Coder 30B Q8 Estimated 24GB 34GB RTX 6000 Ada 48GB A100 80GB Open
DeepSeek Coder V2 16B FP16 Estimated 30GB 42GB RTX 6000 Ada 48GB A100 80GB Open
DeepSeek Coder V2 16B Q4 Estimated 18GB 28GB RTX 6000 Ada 48GB A100 80GB Open
DeepSeek Coder V2 16B Q5 Estimated 20GB 30GB RTX 6000 Ada 48GB A100 80GB Open
DeepSeek Coder V2 16B Q8 Estimated 24GB 34GB RTX 6000 Ada 48GB A100 80GB Open
StarCoder2 15B FP16 Estimated 30GB 42GB RTX 6000 Ada 48GB A100 80GB Open
StarCoder2 15B Q4 Estimated 18GB 28GB RTX 6000 Ada 48GB A100 80GB Open
StarCoder2 15B Q5 Estimated 20GB 30GB RTX 6000 Ada 48GB A100 80GB Open
StarCoder2 15B Q8 Estimated 24GB 34GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 14B FP16 Estimated 22GB 34GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 14B Q4 Estimated 10GB 20GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 14B Q5 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 14B Q8 Estimated 16GB 26GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 Coder 14B FP16 Estimated 22GB 34GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 Coder 14B Q4 Estimated 10GB 20GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 14B Q5 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 14B Q8 Estimated 16GB 26GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 14B FP16 Estimated 22GB 34GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 14B Q4 Estimated 10GB 20GB RTX 3090 24GB A6000 48GB Open
Qwen3 14B Q5 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
Qwen3 14B Q8 Estimated 16GB 26GB RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 13B FP16 Estimated 22GB 34GB RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 13B Q4 Estimated 10GB 20GB RTX 3090 24GB A6000 48GB Open
CodeLlama 13B Q5 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
CodeLlama 13B Q8 Estimated 16GB 26GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 8B FP16 Estimated 18GB 30GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 8B Q4 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
Qwen3 8B Q5 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
Qwen3 8B Q8 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
CodeGemma 7B FP16 Estimated 18GB 30GB RTX 6000 Ada 48GB A100 80GB Open
CodeGemma 7B Q4 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
CodeGemma 7B Q5 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
CodeGemma 7B Q8 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
CodeLlama 7B FP16 Estimated 18GB 30GB RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 7B Q4 Estimated 8GB 10GB RTX 3090 24GB A6000 48GB Open
CodeLlama 7B Q5 Estimated 10GB 12GB RTX 3090 24GB A6000 48GB Open
CodeLlama 7B Q8 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 7B FP16 Estimated 18GB 30GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 7B Q4 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 7B Q5 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 7B Q8 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 7B FP16 Estimated 18GB 30GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 Coder 7B Q4 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 7B Q5 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 7B Q8 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
StarCoder2 7B FP16 Estimated 18GB 30GB RTX 6000 Ada 48GB A100 80GB Open
StarCoder2 7B Q4 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
StarCoder2 7B Q5 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
StarCoder2 7B Q8 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
DeepSeek Coder 6.7B FP16 Estimated 18GB 30GB RTX 6000 Ada 48GB A100 80GB Open
DeepSeek Coder 6.7B Q4 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
DeepSeek Coder 6.7B Q5 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
DeepSeek Coder 6.7B Q8 Estimated 12GB 22GB RTX 3090 24GB A6000 48GB Open
Qwen3 4B FP16 Estimated 16GB 28GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 4B Q4 Estimated 4GB 14GB RTX 3090 24GB A6000 48GB Open
Qwen3 4B Q5 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
Qwen3 4B Q8 Estimated 10GB 20GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 3B FP16 Estimated 16GB 28GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 3B Q4 Estimated 4GB 14GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 3B Q5 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 3B Q8 Estimated 10GB 20GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 3B FP16 Estimated 16GB 28GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 Coder 3B Q4 Estimated 4GB 14GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 3B Q5 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 3B Q8 Estimated 10GB 20GB RTX 3090 24GB A6000 48GB Open
StarCoder2 3B FP16 Estimated 16GB 28GB RTX 6000 Ada 48GB A100 80GB Open
StarCoder2 3B Q4 Estimated 4GB 14GB RTX 3090 24GB A6000 48GB Open
StarCoder2 3B Q5 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
StarCoder2 3B Q8 Estimated 10GB 20GB RTX 3090 24GB A6000 48GB Open
CodeGemma 2B FP16 Estimated 14GB 26GB RTX 6000 Ada 48GB A100 80GB Open
CodeGemma 2B Q4 Estimated 2GB 12GB RTX 3090 24GB A6000 48GB Open
CodeGemma 2B Q5 Estimated 4GB 14GB RTX 3090 24GB A6000 48GB Open
CodeGemma 2B Q8 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
Qwen3 1.7B FP16 Estimated 14GB 26GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 1.7B Q4 Estimated 2GB 12GB RTX 3090 24GB A6000 48GB Open
Qwen3 1.7B Q5 Estimated 4GB 14GB RTX 3090 24GB A6000 48GB Open
Qwen3 1.7B Q8 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 1.5B FP16 Estimated 14GB 26GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 1.5B Q4 Estimated 2GB 12GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 1.5B Q5 Estimated 4GB 14GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 1.5B Q8 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 1.5B FP16 Estimated 14GB 26GB RTX 6000 Ada 48GB A100 80GB Open
Qwen2.5 Coder 1.5B Q4 Estimated 2GB 12GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 1.5B Q5 Estimated 4GB 14GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 1.5B Q8 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
DeepSeek Coder 1.3B FP16 Estimated 14GB 26GB RTX 6000 Ada 48GB A100 80GB Open
DeepSeek Coder 1.3B Q4 Estimated 2GB 12GB RTX 3090 24GB A6000 48GB Open
DeepSeek Coder 1.3B Q5 Estimated 4GB 14GB RTX 3090 24GB A6000 48GB Open
DeepSeek Coder 1.3B Q8 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
Qwen3 0.6B FP16 Estimated 14GB 26GB RTX 6000 Ada 48GB A100 80GB Open
Qwen3 0.6B Q4 Estimated 2GB 12GB RTX 3090 24GB A6000 48GB Open
Qwen3 0.6B Q5 Estimated 4GB 14GB RTX 3090 24GB A6000 48GB Open
Qwen3 0.6B Q8 Estimated 8GB 18GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 0.5B FP16 Estimated 12GB 24GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 0.5B Q4 Estimated 2GB 10GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 0.5B Q5 Estimated 2GB 12GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 0.5B Q8 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 0.5B FP16 Estimated 12GB 24GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 0.5B Q4 Estimated 2GB 10GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 0.5B Q5 Estimated 2GB 12GB RTX 3090 24GB A6000 48GB Open
Qwen2.5 Coder 0.5B Q8 Estimated 6GB 16GB RTX 3090 24GB A6000 48GB Open
Back to all groups Use VRAM calculator Run large models on RunPod Try Vast.ai fallback

We may earn a commission if you click links on this page.