Introduction to ggml
•
157
ggml.ai
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
ggml-org's activity
Post
895
A comprehensive matrix for which format should you use.
Read more on my blog post: https://huggingface.co/blog/ngxson/common-ai-model-formats
Read more on my blog post: https://huggingface.co/blog/ngxson/common-ai-model-formats
| Hardware | GGUF | PyTorch | Safetensors | ONNX |
|-----------------|-----------|------------------------|--------------------------|-------|
| CPU | ✅ (best) | 🟡 | 🟡 | ✅ |
| GPU | ✅ | ✅ | ✅ | ✅ |
| Mobile | ✅ | 🟡 (via executorch) | ❌ | ✅ |
| Apple silicon | ✅ | 🟡 | ✅ (via MLX framework) | ✅ |
- 1 reply
ggerganov
updated
a
collection
about 23 hours ago
ggerganov
updated
a
model
about 23 hours ago
ngxson
authored
a
paper
22 days ago
reach-vb
authored
a
paper
22 days ago
danbev
updated
a
model
22 days ago
danbev
updated
a
collection
22 days ago
danbev
updated
a
model
22 days ago
danbev
updated
a
collection
22 days ago
danbev
updated
a
model
22 days ago
danbev
updated
a
collection
22 days ago
ggerganov
updated
a
collection
28 days ago
ggerganov
updated
a
model
28 days ago
ngxson
updated
a
collection
about 1 month ago
Post
1059
Fun fact: you can get any DeepSeek-R1-Qwen **abliterated** by using one of these LoRA adapters (GGUF available!)
ngxson/extracted-lora-mergekit-677d5c3eea0b6a7661201846
ngxson/extracted-lora-mergekit-677d5c3eea0b6a7661201846
ggerganov
updated
2
models
about 1 month ago
ngxson
updated
a
collection
about 1 month ago