Models
Downloading unsloth/Qwen2.5-Coder-14B-Instruct-GGUF
Default model

Models

No model loaded

Downloading

37.0%unsloth/Qwen2.5-Coder-14B-Instruct-GGUF

6.88 GB of 18.60 GB · 71.0 MB/s · 2m 49s left

GPUApple M4 Pro · 36 GB
RAM31.4 of 48 GB free
CPUApple M4 Pro · 14 cores
Backendmetal
Budget
DeepSeek-Coder-V2-Lite-Instructdeepseek-ai
Ideal fit
15.7BQ4_K_M8.9 GB20.6 GB needed~87.8 tok/s
Qwen2.5-Coder-7B-InstructQwen
Ideal fit
7.6BQ4_K_M4.3 GB6.9 GB needed~34.6 tok/s
Qwen2.5-Coder-14B-InstructQwen
Ideal fit
14.8BQ4_K_M8.4 GB15.2 GB needed~17.8 tok/s
Qwen2.5-Coder-14BQwen
Ideal fit
14.8BQ4_K_M8.4 GB15.2 GB needed~17.8 tok/s
Qwen2.5-Coder-32B-InstructQwen
Ideal fit
32.8BQ4_K_M18.7 GB27.5 GB needed~8 tok/s
Qwen2.5-Coder-32BQwen
Ideal fit
32.8BQ4_K_M18.7 GB27.5 GB needed~8 tok/s
Phi-4-reasoningmicrosoft
Ideal fit
14BQ4_K_M8 GB14.9 GB needed~18.8 tok/s
phi-4microsoft
Ideal fit
14BQ4_K_M8 GB11.8 GB needed~18.8 tok/s
Qwen2.5-Coder-3B-InstructQwen
Ideal fit
3.1BQ4_K_M1.8 GB3.6 GB needed~85.4 tok/s
Qwen2.5-Coder-3BQwen
Ideal fit
3.1BQ4_K_M1.8 GB3.6 GB needed~85.4 tok/s
Qwen2.5-Coder-1.5B-InstructQwen
Ideal fit
1.5BQ4_K_M0.9 GB2.5 GB needed~170.6 tok/s
Qwen2.5-Coder-0.5B-InstructQwen
Ideal fit
0.5BQ4_K_M0.3 GB1.8 GB needed~533.2 tok/s
Qwen2.5-Coder-0.5BQwen
Ideal fit
0.5BQ4_K_M0.3 GB1.8 GB needed~533.2 tok/s
Qwen3-Coder-NextQwen
Too large
80BQ4_K_M45.6 GB49.3 GB needed~0 tok/s

Scheduler

—

Default modelQwen3 coder 30B · Q4_K_MLM Studio (local)