Projector
(beta)
by Cloud Mercato
Log in
DeepSeek-R1 and Ollama3.2 - LLM Performance
Go back to list
Description
Consumption
NVbandwidth
LLM Performance
Judge
Judge Writing
Judge Math
Judge STEM
Judge Coding
Judge Roleplay
Judge Extraction
Judge Humanities
Judge rates
Graph
Pivot table
Filter:
GPU model
None
0
1/10 T4
1/20 T4
1/4*A16
1/5 T4
2GE INTEL fm8 FPGA+1个NVIDIA 3090
3090
A10
A100
A100 80GB
A100 PCIe
A100 PCIe 80GB
A100 SXM 40GB
A100 SXM 80GB
AGF 027
ALINPU 800
AMD MI300X
AMD RX470
AMD S7150
Ali 蚂蚁2.0
Ali-NPU
CPU
FPGA VU13P
FPGA vu9p
GAUDI2
GRID K520
GeForce GTX 1080Ti
GeForce RTX 3080
GeForce RTX 3090
H100 80GB
INTEL ARRIA 10 GX 1150
Intel H3C XG310
Intel HD Graphics P630
NA
NETINT
NETINT T408
NO GPU
NULL
NVIDIA 3090
NVIDIA A10
NVIDIA A10*1
NVIDIA A10*1/12
NVIDIA A10*1/2
NVIDIA A10*1/3
NVIDIA A10*1/6
NVIDIA A10-24Q
NVIDIA A100
NVIDIA A100 40GB PCIe
NVIDIA A100 80G
NVIDIA A100 80G/G39
NVIDIA A100 80GB
NVIDIA A100 80GB PCIe
NVIDIA A100 NVLink 40 GB
NVIDIA A100 PCIE
NVIDIA A100 PCIe 80GB
NVIDIA A100 SXM4 80G
NVIDIA A100-SXM4-40GB
NVIDIA A100-SXM4-80GB
NVIDIA A10G
NVIDIA A16
NVIDIA A30
NVIDIA A40
NVIDIA A4000
NVIDIA A5000
NVIDIA A6000
NVIDIA A800
NVIDIA Ampere 16G
NVIDIA G38
NVIDIA G39
NVIDIA G49
NVIDIA GA107
NVIDIA GH200 PCIe
NVIDIA GPU A
NVIDIA GPU B
NVIDIA GeForce RTX 3070
NVIDIA H100
NVIDIA H100 NVL
NVIDIA H100 PCIe
NVIDIA H100-SXM5-80GB
NVIDIA H200
NVIDIA L4
NVIDIA L4 PCIe
NVIDIA L40
NVIDIA L40S
NVIDIA L40s
NVIDIA L40s PCIe
NVIDIA P100
NVIDIA P4
NVIDIA Quadro RTX6000
NVIDIA RTX 6000
NVIDIA RTX6000
NVIDIA RTX6000*1/2
NVIDIA RTX6000*1/4
NVIDIA T4G
NVIDIA Telsa P40
NVIDIA Telsa T4
NVIDIA Tesla P4
NVIDIA Tesla V100 NVLink 32GB
NVIDIA V100
Nvidia K2
Nvidia P4
Nvidia Tesla V100
PPU 610
PPU 810
Quadro RTX 6000
Quadro RTX 6000 Ada
RTX 6000*1/2
RTX 6000*1/4
RTX A4000
RTX A5000
RTX A6000
RTX A6000 48GB
RTX6000 Ada 48GB
Radeon Instinct MI25
Radeon PRO V620
Radeon Pro V520
Radeon Pro V710
Tesla K80
Tesla M60
Tesla M60-1Q
Tesla P100
Tesla P100-PCIE-16GB
Tesla P4
Tesla P4*1/2
Tesla P4*1/4
Tesla P4*1/8
Tesla P40
Tesla T4
Tesla V100
Tesla V100 32GB
Tesla V100 PCIe
Tesla V100-PCIE-16GB
Tesla V100-PCIE-32GB
Tesla V100-SXM2-16GB
Tesla V100S-PCIE-32GB
VU13P
Xilinx KU115
Xilinx VU9p
cambricon MLU270
intel SG1
intel sg1
Model
Llama 3.3 70b
Llama 3.3 70b FP16
Llama 3.2-Vision 90B
Llama 3.2-Vision 11B
Llama 3.2 1B
Llama 3.2 3B
Llama 3.1 8B
Llama 3.1 8B instruct Q8_0
Llama 3.1 70B
Llama 3.1 70B instruct Q8_0
Llama 3.1 405B
Llama 3 8B
Llama 3 8B FP16
Llama 3 70B
Llama 3 70B FP16
Llama 2 7B
Llama 2 13B
Llama 2 70B
Uncensored Llama 2 7B
Uncensored Llama 2 70B
Gemma 7B
Gemma 2B
Gemma 2 2B
Gemma 2 9B
Gemma 2 27B
Gemma 2 2B FP16
Gemma 2 9B FP16
Gemma 2 27B FP16
Mistral 7B
Mistral 7B FP16
Mistral NeMo
Mistral-Large-Instruct-2407
Mistral-Large-Instruct-2407 FP16
Mistral Large 2 123b
Mistral Large 2 123b-instruct-2411-fp16
Mistral Large 2 123b-instruct-2411-q8_0
Mistral Small 22B
Code Llama 7B
Code Llama 13B
Code Llama 34B
Code Llama 70B
Qwen 0.5B
Qwen 1.8B
Qwen 4B
Qwen 7B
Qwen 14B
Qwen 32B
Qwen 72B
Qwen 110B
Qwen2 0.5B
Qwen2 1.5B
Qwen2 7B
Qwen2 72B
Qwen2.5 0.5B
Qwen2.5 1.5B
Qwen2.5 3B
Qwen2.5 7B
Qwen2.5 14B
Qwen2.5 32B
Qwen2.5 72B
Nemotron-Mini-4B
Mixtral 8x7b
Mixtral 8x22b
Mixtral 8x7b FP16
Mixtral 8x22b FP16
Uncensored Mixtral 8x7b
Uncensored Mixtral 8x22b
LLaVA 7B
LLaVA 13B
LLaVA 34B
LLaVA 7B Mistral FP16
LLaVA 13B Vicuna FP16
LLaVA 34B FP16
LLaVA Llama3 8B
LLaVA Llama3 8B FP16
LLaVA 7B v1.6 Mistral Q8_0
LLaVA 13B v1.6 Vicuna Q8_0
LLaVA 34B v1.6 Q8_0
Phi-4 14B
Phi-3 Mini
Phi-3 Medium
Phi-3 Mini 128K
Phi-3 Medium 128K
Phi-3.5 Mini
Phi-3.5 Mini FP16
SmolLM 135m
SmolLM 360m
SmolLM 1.7b
Firefunction-v2
DeepSeek R1 1.5B
DeepSeek R1 7B
DeepSeek R1 8B
DeepSeek R1 14B
DeepSeek R1 32B
DeepSeek R1 70B
DeepSeek R1 671B
DeepSeek Coder 1.3B
DeepSeek Coder 6.7B
DeepSeek Coder 33B
DeepSeek-Coder-v2 16B
DeepSeek-Coder-v2 236B
Orca Mini 3B
Orca Mini 7B
Orca Mini 13B
Orca Mini 70B
Orca 2
Orca 2 13B
Vicuna 7B
Vicuna 13B
Vicuna 33B
WizardLM-2 7B
WizardLM-2 8x22B
WizardLM
CodeGemma 7B
CodeGemma 2B
Command R
Command R FP16
Command R+
Command R+ FP16
NOMIC
mxbai-embed-large
Yi 6b
Yi 9b
Yi 34b
TinyLlama
GLM4
GLM4 FP16
CodeGeeX4
CodeGeeX4 FP16
StarCoder2 3b
StarCoder2 7b
StarCoder2 15b
Rate: