Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for BGE-M3 Multilingual Embedding 567M quantized in FP16 Uncompressed Native deployed on NVIDIA H100 80GB SXM5.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for BGE-M3 Multilingual Embedding 567M quantized in BF16 Bfloat16 Mixed Precision deployed on NVIDIA H200 141GB HBM3e.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for BGE-M3 Multilingual Embedding 567M quantized in FP8 Scaled Native Hopper deployed on NVIDIA B200 192GB Blackwell.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for BGE-M3 Multilingual Embedding 567M quantized in INT8 SmoothQuant Precision deployed on NVIDIA A100 80GB PCIe.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for BGE-M3 Multilingual Embedding 567M quantized in AWQ 4-Bit Activation-Aware deployed on NVIDIA RTX 4090 24GB GDDR6X.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for BGE-M3 Multilingual Embedding 567M quantized in GPTQ 4-Bit Second-Order deployed on NVIDIA L40S 48GB Ada Lovelace.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for BGE-M3 Multilingual Embedding 567M quantized in GGUF Q4_K_M Medium Quant deployed on AMD Instinct MI300X 192GB.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for LLaVA-NeXT 72B Multimodal Vision quantized in FP16 Uncompressed Native deployed on NVIDIA H100 80GB SXM5.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for LLaVA-NeXT 72B Multimodal Vision quantized in BF16 Bfloat16 Mixed Precision deployed on NVIDIA H200 141GB HBM3e.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for LLaVA-NeXT 72B Multimodal Vision quantized in FP8 Scaled Native Hopper deployed on NVIDIA B200 192GB Blackwell.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for LLaVA-NeXT 72B Multimodal Vision quantized in INT8 SmoothQuant Precision deployed on NVIDIA A100 80GB PCIe.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for LLaVA-NeXT 72B Multimodal Vision quantized in AWQ 4-Bit Activation-Aware deployed on NVIDIA RTX 4090 24GB GDDR6X.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for LLaVA-NeXT 72B Multimodal Vision quantized in GPTQ 4-Bit Second-Order deployed on NVIDIA L40S 48GB Ada Lovelace.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for LLaVA-NeXT 72B Multimodal Vision quantized in GGUF Q4_K_M Medium Quant deployed on AMD Instinct MI300X 192GB.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for MiniCPM-V 2.6 8B Omni-Vision quantized in FP16 Uncompressed Native deployed on NVIDIA H100 80GB SXM5.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for MiniCPM-V 2.6 8B Omni-Vision quantized in BF16 Bfloat16 Mixed Precision deployed on NVIDIA H200 141GB HBM3e.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for MiniCPM-V 2.6 8B Omni-Vision quantized in FP8 Scaled Native Hopper deployed on NVIDIA B200 192GB Blackwell.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for MiniCPM-V 2.6 8B Omni-Vision quantized in INT8 SmoothQuant Precision deployed on NVIDIA A100 80GB PCIe.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for MiniCPM-V 2.6 8B Omni-Vision quantized in AWQ 4-Bit Activation-Aware deployed on NVIDIA RTX 4090 24GB GDDR6X.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for MiniCPM-V 2.6 8B Omni-Vision quantized in GPTQ 4-Bit Second-Order deployed on NVIDIA L40S 48GB Ada Lovelace.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for MiniCPM-V 2.6 8B Omni-Vision quantized in GGUF Q4_K_M Medium Quant deployed on AMD Instinct MI300X 192GB.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for InternLM2.5 20B 1M Context quantized in FP16 Uncompressed Native deployed on NVIDIA H100 80GB SXM5.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for InternLM2.5 20B 1M Context quantized in BF16 Bfloat16 Mixed Precision deployed on NVIDIA H200 141GB HBM3e.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for InternLM2.5 20B 1M Context quantized in FP8 Scaled Native Hopper deployed on NVIDIA B200 192GB Blackwell.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for InternLM2.5 20B 1M Context quantized in INT8 SmoothQuant Precision deployed on NVIDIA A100 80GB PCIe.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for InternLM2.5 20B 1M Context quantized in AWQ 4-Bit Activation-Aware deployed on NVIDIA RTX 4090 24GB GDDR6X.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for InternLM2.5 20B 1M Context quantized in GPTQ 4-Bit Second-Order deployed on NVIDIA L40S 48GB Ada Lovelace.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for InternLM2.5 20B 1M Context quantized in GGUF Q4_K_M Medium Quant deployed on AMD Instinct MI300X 192GB.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for Baichuan-2 13B Enterprise Chinese quantized in FP16 Uncompressed Native deployed on NVIDIA H100 80GB SXM5.
Exact VRAM memory allocation, dynamic KV-cache requirements, and tensor parallelism slicing for Baichuan-2 13B Enterprise Chinese quantized in BF16 Bfloat16 Mixed Precision deployed on NVIDIA H200 141GB HBM3e.