Fit for Apple M2 Ultra

64GB VRAM · Apple · General · INT4

✓

Fits on 1 GPU

(12 models)
1
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB
NVIDIA · 74.0B · MoE · INT4

Score

11.37

tok/s (est.)

36.1

Community tok/s

—

VRAM (est.)

39.2GB

License

OpenMDW License Agreement v1.1

2
Kolibri-1
Aleph Alpha · 78.1B · MoE · INT4

Score

0.85

tok/s (est.)

89.4

Community tok/s

—

VRAM (est.)

41.1GB

License

Apache License 2.0

3
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

4
Gemma 3 27B PT
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

5
Qwen3-Next-80B-A3B-Thinking
Qwen · 80.0B · MoE · INT4

Score

0.82

tok/s (est.)

101.7

Community tok/s

—

VRAM (est.)

42.1GB

License

Apache License 2.0

6
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

7
Qwen3.5-27B
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

8
Qwen3.8-27B
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

9
Clef
Cloudflare · 27.0B · INT4

Score

0.71

tok/s (est.)

40.0

Community tok/s

—

VRAM (est.)

15.2GB

License

Apache License 2.0

10
Qwen-AgentWorld-35B-A3B
Qwen Team (Alibaba Cloud) · 35.0B · MoE · INT4

Score

0.7

tok/s (est.)

101.7

Community tok/s

—

VRAM (est.)

18.5GB

License

Apache License 2.0

11
Ornith-1.5-35B-A3B
Ornith AI · 36.0B · MoE · INT4

Score

0.69

tok/s (est.)

101.7

Community tok/s

—

VRAM (est.)

19.0GB

License

MIT License

12
Qwen3.6-35B-A3B
Qwen Team (Alibaba Cloud) · 35.0B · MoE · INT4

Score

0.67

tok/s (est.)

101.7

Community tok/s

—

VRAM (est.)

18.5GB

License

Apache License 2.0

⚠

Needs 8+ GPUs

(12 models)
1
Muse-Spark-Open-816B-A42B
Meta Superintelligence Lab · 816.0B · int4 · 8× GPU

Score

0.91

tok/s (est.)

60.5

Community tok/s

—

VRAM/GPU (est.)

53.8GB

License

Muse Model License

2
DeepSeek-V4.1-Flash
DeepSeek · 763.0B · int4 · 8× GPU

Score

0.89

tok/s (est.)

145.9

Community tok/s

—

VRAM/GPU (est.)

50.1GB

License

MIT License

3
Qwen3.8-Flash-Next
Qwen Team (Alibaba) · 125.0B · int4 · 2× GPU

Score

0.87

tok/s (est.)

101.7

Community tok/s

—

VRAM/GPU (est.)

32.9GB

License

Qwen Community License 1.0

4
GLM-5.3-Flash
Zhipu AI · 320.0B · int4 · 4× GPU

Score

0.87

tok/s (est.)

69.9

Community tok/s

—

VRAM/GPU (est.)

42.2GB

License

MIT License

5
DeepSeek-V4-Pro-0813
DeepSeek · 1.7T · int4 · 17× GPU

Score

0.83

tok/s (est.)

105.5

Community tok/s

—

VRAM/GPU (est.)

52.6GB

License

MIT License

6
Qwen3.5-122B-A10B
Qwen Team (Alibaba Cloud) · 122.0B · int4 · 2× GPU

Score

0.82

tok/s (est.)

63.3

Community tok/s

—

VRAM/GPU (est.)

32.2GB

License

Apache License 2.0

7
GPT-OSS-120B
OpenAI · 116.8B · int4 · 2× GPU

Score

0.78

tok/s (est.)

117.1

Community tok/s

—

VRAM/GPU (est.)

30.8GB

License

Apache License 2.0

8
GLM-5.3
Zhipu AI · 753.3B · int4 · 8× GPU

Score

0.75

tok/s (est.)

59.1

Community tok/s

—

VRAM/GPU (est.)

49.6GB

License

GLM-5.3 License

9
Hy4 preview
Tencent · 770.0B · int4 · 8× GPU

Score

0.74

tok/s (est.)

52.3

Community tok/s

—

VRAM/GPU (est.)

50.8GB

License

Apache License 2.0

10
Kimi K3
Moonshot AI · 2.8T · int4 · 28× GPU

Score

0.73

tok/s (est.)

83.6

Community tok/s

—

VRAM/GPU (est.)

52.6GB

License

Kimi K3 License

11
DeepSeek-V4-Pro
DeepSeek · 1.6T · int4 · 16× GPU

Score

0.7

tok/s (est.)

11.1

Community tok/s

—

VRAM/GPU (est.)

56.4GB

License

MIT License

12
DeepSeek-V4-Pro
DeepSeek · 1.6T · int4 · 16× GPU

Score

0.69

tok/s (est.)

99.8

Community tok/s

—

VRAM/GPU (est.)

52.6GB

License

MIT License