HoML Logo

HoML
← Back to Models

Qwen2

Qwen2 is a series of large language models from Alibaba Cloud. They are Transformer-based models with SwiGLU activation, attention QKV bias, and group query attention. They have strong performance in language understanding, generation, multilingual capabilities, coding, mathematics, and reasoning.

qwen2-1.5b

1.5B parameters Base

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:1.5b

Resource Requirements

Quantization Disk Space GPU Memory
BF16 3 GB 3 GB

qwen2-1.5b-instruct

1.5B parameters Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:1.5b-instruct

Resource Requirements

Quantization Disk Space GPU Memory
BF16 3 GB 3 GB

qwen2-1.5b-instruct-8bit

1.5B parameters Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:1.5b-instruct-8bit

Resource Requirements

Quantization Disk Space GPU Memory
8-bit 1.5 GB 1.5 GB

qwen2-1.5b-instruct-4bit

1.5B parameters Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:1.5b-instruct-4bit

Resource Requirements

Quantization Disk Space GPU Memory
4-bit 0.75 GB 0.75 GB

qwen2-7b

7B parameters Base

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:7b

Resource Requirements

Quantization Disk Space GPU Memory
BF16 14 GB 14 GB

qwen2-7b-instruct

7B parameters Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:7b-instruct

Resource Requirements

Quantization Disk Space GPU Memory
BF16 14 GB 14 GB

qwen2-7b-instruct-8bit

7B parameters Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:7b-instruct-8bit

Resource Requirements

Quantization Disk Space GPU Memory
8-bit 7 GB 7 GB

qwen2-7b-instruct-4bit

7B parameters Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:7b-instruct-4bit

Resource Requirements

Quantization Disk Space GPU Memory
4-bit 3.5 GB 3.5 GB

qwen2-72b

72B parameters Base

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:72b

Resource Requirements

Quantization Disk Space GPU Memory
BF16 144 GB 144 GB

qwen2-72b-instruct

72B parameters Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:72b-instruct

Resource Requirements

Quantization Disk Space GPU Memory
BF16 144 GB 144 GB

qwen2-72b-instruct-8bit

72B parameters Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:72b-instruct-8bit

Resource Requirements

Quantization Disk Space GPU Memory
8-bit 72 GB 72 GB

qwen2-72b-instruct-4bit

72B parameters Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:72b-instruct-4bit

Resource Requirements

Quantization Disk Space GPU Memory
4-bit 36 GB 36 GB

qwen2-57b-a14b

57B parameters MoE

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:57b-a14b

Resource Requirements

Quantization Disk Space GPU Memory
BF16 114 GB 114 GB

qwen2-57b-a14b-instruct

57B parameters MoE-Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:57b-a14b-instruct

Resource Requirements

Quantization Disk Space GPU Memory
BF16 114 GB 114 GB

qwen2-57b-a14b-instruct-8bit

57B parameters MoE-Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:57b-a14b-instruct-8bit

Resource Requirements

Quantization Disk Space GPU Memory
8-bit 57 GB 57 GB

qwen2-57b-a14b-instruct-4bit

57B parameters MoE-Instruction-Tuned

Pull this model

Use the following command with the HoML CLI:

homl pull qwen2:57b-a14b-instruct-4bit

Resource Requirements

Quantization Disk Space GPU Memory
4-bit 28.5 GB 28.5 GB