Your GPU

Fit for GeForce RTX 3080 Ti

12GB VRAM · NVIDIA · General · INT4

✓

Fits on 1 GPU

(12 models)

1

SparkLLM (XHToken) · 4.0B · INT4

Score

0.65

tok/s (est.)

248.0

Community tok/s

—

VRAM (est.)

2.3GB

License

Apache License 2.0

2

Google DeepMind · 12.0B · INT4

Score

0.64

tok/s (est.)

97.1

Community tok/s

—

VRAM (est.)

6.8GB

License

Gemma Terms of Use

3

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

4

OpenBMB · 2.5B · INT4

Score

0.59

tok/s (est.)

348.3

Community tok/s

—

VRAM (est.)

1.4GB

License

Apache License 2.0

5

Google · 11.9B · INT4

Score

0.49

tok/s (est.)

97.5

Community tok/s

—

VRAM (est.)

6.7GB

License

Apache License 2.0

6

Qwen · 4.0B · INT4

Score

0.45

tok/s (est.)

248.0

Community tok/s

—

VRAM (est.)

2.3GB

License

Apache License 2.0

7

IBM · 3.0B · INT4

Score

0.42

tok/s (est.)

307.7

Community tok/s

—

VRAM (est.)

1.7GB

License

Apache License 2.0

8

DeepReinforce AI · 9.0B · INT4

Score

0.42

tok/s (est.)

125.8

Community tok/s

—

VRAM (est.)

5.1GB

License

MIT License

9

Cloudflare · 9.0B · INT4

Score

0.41

tok/s (est.)

125.8

Community tok/s

—

VRAM (est.)

5.1GB

License

Apache License 2.0

10

Spark-X2.5-1.7B

SparkLLM (XHToken) · 2.0B · INT4

Score

0.36

tok/s (est.)

405.4

Community tok/s

—

VRAM (est.)

1.1GB

License

Apache License 2.0

11

Nemotron-3-Nano-4B

NVIDIA · 4.0B · INT4

Score

0.26

tok/s (est.)

249.4

Community tok/s

—

VRAM (est.)

2.2GB

License

NVIDIA Nemotron Open Model License

12

LiquidAI · 2.7B · INT4

Score

0.25

tok/s (est.)

332.6

Community tok/s

—

VRAM (est.)

1.5GB

License

LFM Open License v1.0

⚠

Needs 4+ GPUs

(12 models)

1

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

NVIDIA · 74.0B · int4 · 4× GPU

Score

11.37

tok/s (est.)

147.6

Community tok/s

—

VRAM/GPU (est.)

9.8GB

License

OpenMDW License Agreement v1.1

2

Muse-Spark-Open-816B-A42B

Meta Superintelligence Lab · 816.0B · int4 · 43× GPU

Score

0.91

tok/s (est.)

289.8

Community tok/s

—

VRAM/GPU (est.)

10.0GB

License

Muse Model License

3

DeepSeek-V4.1-Flash

DeepSeek · 763.0B · int4 · 40× GPU

Score

0.89

tok/s (est.)

514.2

Community tok/s

—

VRAM/GPU (est.)

10.0GB

License

MIT License

4

Qwen3.8-Flash-Next

Qwen Team (Alibaba) · 125.0B · int4 · 7× GPU

Score

0.87

tok/s (est.)

318.6

Community tok/s

—

VRAM/GPU (est.)

9.4GB

License

Qwen Community License 1.0

5

Zhipu AI · 320.0B · int4 · 17× GPU

Score

0.87

tok/s (est.)

272.8

Community tok/s

—

VRAM/GPU (est.)

9.9GB

License

MIT License

6

Aleph Alpha · 78.1B · int4 · 5× GPU

Score

0.85

tok/s (est.)

369.4

Community tok/s

—

VRAM/GPU (est.)

8.2GB

License

Apache License 2.0

7

Bonsai 2 27B — GGUF

Prism ML · 27.4B · int4 · 2× GPU

Score

0.85

tok/s (est.)

86.0

Community tok/s

—

VRAM/GPU (est.)

7.7GB

License

Apache License 2.0

8

Google DeepMind · 27.0B · int4 · 2× GPU

Score

0.84

tok/s (est.)

87.1

Community tok/s

—

VRAM/GPU (est.)

7.6GB

License

Gemma Terms of Use

9

Qwen3-Next-80B-A3B-Thinking

Qwen · 80.0B · int4 · 5× GPU

Score

0.82

tok/s (est.)

405.2

Community tok/s

—

VRAM/GPU (est.)

8.4GB

License

Apache License 2.0

10

Qwen3.5-122B-A10B

Qwen Team (Alibaba Cloud) · 122.0B · int4 · 7× GPU

Score

0.82

tok/s (est.)

215.9

Community tok/s

—

VRAM/GPU (est.)

9.2GB

License

Apache License 2.0

11

Xing4.0-29B-A4B

China Telecom AI · 31.2B · int4 · 2× GPU

Score

0.82

tok/s (est.)

163.3

Community tok/s

—

VRAM/GPU (est.)

8.3GB

License

Apache License 2.0

12

OpenAI · 116.8B · int4 · 7× GPU

Score

0.78

tok/s (est.)

355.3

Community tok/s

—

VRAM/GPU (est.)

8.8GB

License

Apache License 2.0