Your GPU

Fit for AMD Radeon RX 7900 XT

20GB VRAM · AMD · General · INT4

✓

Fits on 1 GPU

(12 models)

1

Bonsai 2 27B — GGUF

Prism ML · 27.4B · INT4

Score

0.85

tok/s (est.)

39.5

Community tok/s

—

VRAM (est.)

15.4GB

License

Apache License 2.0

2

Google DeepMind · 27.0B · INT4

Score

0.84

tok/s (est.)

40.0

Community tok/s

—

VRAM (est.)

15.2GB

License

Gemma Terms of Use

3

Xing4.0-29B-A4B

China Telecom AI · 31.2B · MoE · INT4

Score

0.82

tok/s (est.)

78.1

Community tok/s

—

VRAM (est.)

16.5GB

License

Apache License 2.0

4

Qwen Team (Alibaba Cloud) · 27.0B · INT4

Score

0.77

tok/s (est.)

40.0

Community tok/s

—

VRAM (est.)

15.2GB

License

Apache License 2.0

5

Qwen Team (Alibaba Cloud) · 27.0B · INT4

Score

0.76

tok/s (est.)

40.0

Community tok/s

—

VRAM (est.)

15.2GB

License

Apache License 2.0

6

Cloudflare · 27.0B · INT4

Score

0.71

tok/s (est.)

40.0

Community tok/s

—

VRAM (est.)

15.2GB

License

Apache License 2.0

7

SparkLLM (XHToken) · 4.0B · INT4

Score

0.65

tok/s (est.)

223.6

Community tok/s

—

VRAM (est.)

2.3GB

License

Apache License 2.0

8

Google DeepMind · 12.0B · INT4

Score

0.64

tok/s (est.)

86.1

Community tok/s

—

VRAM (est.)

6.8GB

License

Gemma Terms of Use

9

Qwen Team (Alibaba Cloud) · 27.0B · INT4

Score

0.62

tok/s (est.)

40.0

Community tok/s

—

VRAM (est.)

15.2GB

License

Apache License 2.0

10

LiquidAI · 24.0B · MoE · INT4

Score

0.6

tok/s (est.)

122.1

Community tok/s

—

VRAM (est.)

12.7GB

License

LFM Open License v1.0

11

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

12

OpenBMB · 2.5B · INT4

Score

0.59

tok/s (est.)

317.8

Community tok/s

—

VRAM (est.)

1.4GB

License

Apache License 2.0

⚠

Needs 3+ GPUs

(12 models)

1

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

NVIDIA · 74.0B · int4 · 3× GPU

Score

11.37

tok/s (est.)

101.7

Community tok/s

—

VRAM/GPU (est.)

13.1GB

License

OpenMDW License Agreement v1.1

2

Muse-Spark-Open-816B-A42B

Meta Superintelligence Lab · 816.0B · int4 · 26× GPU

Score

0.91

tok/s (est.)

175.2

Community tok/s

—

VRAM/GPU (est.)

16.5GB

License

Muse Model License

3

DeepSeek-V4.1-Flash

DeepSeek · 763.0B · int4 · 24× GPU

Score

0.89

tok/s (est.)

346.6

Community tok/s

—

VRAM/GPU (est.)

16.7GB

License

MIT License

4

Qwen3.8-Flash-Next

Qwen Team (Alibaba) · 125.0B · int4 · 4× GPU

Score

0.87

tok/s (est.)

186.3

Community tok/s

—

VRAM/GPU (est.)

16.5GB

License

Qwen Community License 1.0

5

Zhipu AI · 320.0B · int4 · 10× GPU

Score

0.87

tok/s (est.)

159.8

Community tok/s

—

VRAM/GPU (est.)

16.9GB

License

MIT License

6

Aleph Alpha · 78.1B · int4 · 3× GPU

Score

0.85

tok/s (est.)

230.8

Community tok/s

—

VRAM/GPU (est.)

13.7GB

License

Apache License 2.0

7

DeepSeek-V4-Pro-0813

DeepSeek · 1.7T · int4 · 54× GPU

Score

0.83

tok/s (est.)

277.7

Community tok/s

—

VRAM/GPU (est.)

16.6GB

License

MIT License

8

Qwen3-Next-80B-A3B-Thinking

Qwen · 80.0B · int4 · 3× GPU

Score

0.82

tok/s (est.)

257.8

Community tok/s

—

VRAM/GPU (est.)

14.0GB

License

Apache License 2.0

9

Qwen3.5-122B-A10B

Qwen Team (Alibaba Cloud) · 122.0B · int4 · 4× GPU

Score

0.82

tok/s (est.)

119.8

Community tok/s

—

VRAM/GPU (est.)

16.1GB

License

Apache License 2.0

10

OpenAI · 116.8B · int4 · 4× GPU

Score

0.78

tok/s (est.)

211.9

Community tok/s

—

VRAM/GPU (est.)

15.4GB

License

Apache License 2.0

11

Zhipu AI · 753.3B · int4 · 24× GPU

Score

0.75

tok/s (est.)

160.3

Community tok/s

—

VRAM/GPU (est.)

16.5GB

License

GLM-5.3 License

12

Tencent · 770.0B · int4 · 25× GPU

Score

0.74

tok/s (est.)

148.5

Community tok/s

—

VRAM/GPU (est.)

16.2GB

License

Apache License 2.0