Your GPU

Fit for GeForce GTX 1650

4GB VRAM · NVIDIA · General · INT4

✓

Fits on 1 GPU

(12 models)

1

SparkLLM (XHToken) · 4.0B · INT4

Score

0.65

tok/s (est.)

63.4

Community tok/s

—

VRAM (est.)

2.3GB

License

Apache License 2.0

2

Qwen3-Coder-Next

Qwen · 0.1K · MoE · INT4

Score

0.59

tok/s (est.)

1111.1

Community tok/s

—

VRAM (est.)

—GB

License

Apache License 2.0

3

OpenBMB · 2.5B · INT4

Score

0.59

tok/s (est.)

97.4

Community tok/s

—

VRAM (est.)

1.4GB

License

Apache License 2.0

4

Qwen · 4.0B · INT4

Score

0.45

tok/s (est.)

63.4

Community tok/s

—

VRAM (est.)

2.3GB

License

Apache License 2.0

5

IBM · 3.0B · INT4

Score

0.42

tok/s (est.)

82.9

Community tok/s

—

VRAM (est.)

1.7GB

License

Apache License 2.0

6

Spark-X2.5-1.7B

SparkLLM (XHToken) · 2.0B · INT4

Score

0.36

tok/s (est.)

119.9

Community tok/s

—

VRAM (est.)

1.1GB

License

Apache License 2.0

7

Nemotron-3-Nano-4B

NVIDIA · 4.0B · INT4

Score

0.26

tok/s (est.)

63.8

Community tok/s

—

VRAM (est.)

2.2GB

License

NVIDIA Nemotron Open Model License

8

LiquidAI · 2.7B · INT4

Score

0.25

tok/s (est.)

91.7

Community tok/s

—

VRAM (est.)

1.5GB

License

LFM Open License v1.0

9

Google · 4.5B · INT4

Score

0.25

tok/s (est.)

56.7

Community tok/s

—

VRAM (est.)

2.5GB

License

Apache License 2.0

10

Google DeepMind · 4.0B · INT4

Score

0.22

tok/s (est.)

63.4

Community tok/s

—

VRAM (est.)

2.3GB

License

Gemma Terms of Use

11

Qwen Team (Alibaba Cloud) · 2.0B · INT4

Score

0.15

tok/s (est.)

119.9

Community tok/s

—

VRAM (est.)

1.1GB

License

Apache License 2.0

12

Google · 2.3B · INT4

Score

0.11

tok/s (est.)

105.8

Community tok/s

—

VRAM (est.)

1.3GB

License

Apache License 2.0

⚠

Needs 12+ GPUs

(12 models)

1

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB

NVIDIA · 74.0B · int4 · 12× GPU

Score

11.37

tok/s (est.)

98.0

Community tok/s

—

VRAM/GPU (est.)

3.3GB

License

OpenMDW License Agreement v1.1

2

Qwen3.8-Flash-Next

Qwen Team (Alibaba) · 125.0B · int4 · 20× GPU

Score

0.87

tok/s (est.)

216.4

Community tok/s

—

VRAM/GPU (est.)

3.3GB

License

Qwen Community License 1.0

3

Zhipu AI · 320.0B · int4 · 50× GPU

Score

0.87

tok/s (est.)

186.4

Community tok/s

—

VRAM/GPU (est.)

3.4GB

License

MIT License

4

Aleph Alpha · 78.1B · int4 · 13× GPU

Score

0.85

tok/s (est.)

238.2

Community tok/s

—

VRAM/GPU (est.)

3.2GB

License

Apache License 2.0

5

Bonsai 2 27B — GGUF

Prism ML · 27.4B · int4 · 5× GPU

Score

0.85

tok/s (est.)

47.0

Community tok/s

—

VRAM/GPU (est.)

3.1GB

License

Apache License 2.0

6

Google DeepMind · 27.0B · int4 · 5× GPU

Score

0.84

tok/s (est.)

47.6

Community tok/s

—

VRAM/GPU (est.)

3.0GB

License

Gemma Terms of Use

7

Qwen3-Next-80B-A3B-Thinking

Qwen · 80.0B · int4 · 13× GPU

Score

0.82

tok/s (est.)

265.8

Community tok/s

—

VRAM/GPU (est.)

3.2GB

License

Apache License 2.0

8

Qwen3.5-122B-A10B

Qwen Team (Alibaba Cloud) · 122.0B · int4 · 20× GPU

Score

0.82

tok/s (est.)

140.8

Community tok/s

—

VRAM/GPU (est.)

3.2GB

License

Apache License 2.0

9

Xing4.0-29B-A4B

China Telecom AI · 31.2B · int4 · 5× GPU

Score

0.82

tok/s (est.)

92.4

Community tok/s

—

VRAM/GPU (est.)

3.3GB

License

Apache License 2.0

10

OpenAI · 116.8B · int4 · 19× GPU

Score

0.78

tok/s (est.)

235.4

Community tok/s

—

VRAM/GPU (est.)

3.2GB

License

Apache License 2.0

11

Qwen Team (Alibaba Cloud) · 27.0B · int4 · 5× GPU

Score

0.77

tok/s (est.)

47.6

Community tok/s

—

VRAM/GPU (est.)

3.0GB

License

Apache License 2.0

12

Qwen Team (Alibaba Cloud) · 27.0B · int4 · 5× GPU

Score

0.76

tok/s (est.)

47.6

Community tok/s

—

VRAM/GPU (est.)

3.0GB

License

Apache License 2.0