Closed-Weight Models

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

RAM planning is included because Ollama may spill layers to CPU when VRAM is tight, especially with long context.

Model Data VRAM min VRAM optimal System RAM RTX 3090 fit Best local GPU Cloud fallback Detail
Llama 4 128X17B FP16 Estimated 430GB 442GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 4 128X17B Q4 Estimated 418GB 428GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 4 128X17B Q5 Estimated 420GB 430GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 4 128X17B Q8 Estimated 424GB 434GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 3.1 405B FP16 Estimated 225GB 237GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 3.1 405B Q4 Estimated 213GB 223GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 3.1 405B Q5 Estimated 215GB 225GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 3.1 405B Q8 Estimated 219GB 229GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 4 16X17B FP16 Estimated 225GB 237GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 4 16X17B Q4 Estimated 40GB 48GB 64GB+ Cloud / larger GPU RTX 6000 Ada 48GB A100 80GB Open
Llama 4 16X17B Q5 Estimated 48GB 50GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 4 16X17B Q8 Estimated 219GB 229GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 3.2 Vision 90B FP16 Estimated 80GB 92GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
Llama 3.2 Vision 90B Q4 Estimated 68GB 78GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3.2 Vision 90B Q5 Estimated 70GB 80GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3.2 Vision 90B Q8 Estimated 74GB 84GB 128GB+ Cloud / larger GPU Cloud-first (no practical single-GPU local) H100/H200 class Open
CodeLlama 70B FP16 Estimated 50GB 62GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
CodeLlama 70B Q4 Estimated 38GB 48GB 64GB+ Cloud / larger GPU RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 70B Q5 Estimated 40GB 50GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
CodeLlama 70B Q8 Estimated 44GB 54GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 2 70B FP16 Estimated 50GB 62GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 2 70B Q4 Estimated 38GB 48GB 64GB+ Cloud / larger GPU RTX 6000 Ada 48GB A100 80GB Open
Llama 2 70B Q5 Estimated 40GB 50GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 2 70B Q8 Estimated 44GB 54GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3 70B FP16 Estimated 50GB 62GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3 70B Q4 Estimated 38GB 48GB 64GB+ Cloud / larger GPU RTX 6000 Ada 48GB A100 80GB Open
Llama 3 70B Q5 Estimated 40GB 50GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3 70B Q8 Estimated 44GB 54GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3.1 70B FP16 Estimated 50GB 62GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3.1 70B Q4 Estimated 38GB 48GB 64GB+ Cloud / larger GPU RTX 6000 Ada 48GB A100 80GB Open
Llama 3.1 70B Q5 Estimated 40GB 50GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3.1 70B Q8 Estimated 44GB 54GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3.3 70B FP16 Estimated 50GB 62GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3.3 70B Q4 Estimated 40GB 48GB 64GB+ Cloud / larger GPU RTX 6000 Ada 48GB A100 80GB Open
Llama 3.3 70B Q5 Estimated 48GB 50GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
Llama 3.3 70B Q8 Estimated 44GB 54GB 128GB+ Cloud / larger GPU Dual RTX 4090 (model parallel) A100 80GB Open
CodeLlama 34B FP16 Estimated 30GB 42GB 64GB+ Cloud / larger GPU RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 34B Q4 Estimated 18GB 28GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 34B Q5 Estimated 20GB 30GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 34B Q8 Estimated 24GB 34GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Mistral Small 24B FP16 Estimated 30GB 42GB 64GB+ Cloud / larger GPU RTX 6000 Ada 48GB A100 80GB Open
Mistral Small 24B Q4 Estimated 18GB 28GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Mistral Small 24B Q5 Estimated 20GB 30GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Mistral Small 24B Q8 Estimated 24GB 34GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Mistral Small 22B FP16 Estimated 30GB 42GB 64GB+ Cloud / larger GPU RTX 6000 Ada 48GB A100 80GB Open
Mistral Small 22B Q4 Estimated 18GB 28GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Mistral Small 22B Q5 Estimated 20GB 30GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Mistral Small 22B Q8 Estimated 24GB 34GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 13B FP16 Estimated 22GB 34GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 13B Q4 Estimated 10GB 20GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
CodeLlama 13B Q5 Estimated 12GB 22GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
CodeLlama 13B Q8 Estimated 16GB 26GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Llama 2 13B FP16 Estimated 22GB 34GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Llama 2 13B Q4 Estimated 10GB 20GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 2 13B Q5 Estimated 12GB 22GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 2 13B Q8 Estimated 16GB 26GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Llama 3.2 Vision 11B FP16 Estimated 22GB 34GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Llama 3.2 Vision 11B Q4 Estimated 10GB 20GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.2 Vision 11B Q5 Estimated 12GB 22GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.2 Vision 11B Q8 Estimated 16GB 26GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Llama 3 8B FP16 Estimated 18GB 30GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Llama 3 8B Q4 Estimated 6GB 16GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3 8B Q5 Estimated 8GB 18GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3 8B Q8 Estimated 12GB 22GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.1 8B FP16 Estimated 18GB 30GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Llama 3.1 8B Q4 Estimated 6GB 16GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.1 8B Q5 Estimated 8GB 18GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.1 8B Q8 Estimated 12GB 22GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
CodeLlama 7B FP16 Estimated 18GB 30GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
CodeLlama 7B Q4 Estimated 6GB 16GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
CodeLlama 7B Q5 Estimated 8GB 18GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
CodeLlama 7B Q8 Estimated 12GB 22GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 2 7B FP16 Estimated 18GB 30GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Llama 2 7B Q4 Estimated 6GB 16GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 2 7B Q5 Estimated 8GB 18GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 2 7B Q8 Estimated 12GB 22GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.2 3B FP16 Estimated 16GB 28GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Llama 3.2 3B Q4 Estimated 4GB 14GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.2 3B Q5 Estimated 6GB 16GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.2 3B Q8 Estimated 10GB 20GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.2 1B FP16 Estimated 14GB 26GB 64GB+ Borderline RTX 6000 Ada 48GB A100 80GB Open
Llama 3.2 1B Q4 Estimated 2GB 12GB 16GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.2 1B Q5 Estimated 4GB 14GB 32GB+ Comfortable RTX 3090 24GB A6000 48GB Open
Llama 3.2 1B Q8 Estimated 8GB 18GB 32GB+ Comfortable 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.