Jan Grzybek

jangrzybek's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 3 days ago

AmpereComputing/qwen-3-a3b-30b-thinking-gguf

31B • Updated 3 days ago • 107

updated a collection 3 days ago

Qwen 3

Collection

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp • 11 items • Updated 3 days ago • 2

published a model 3 days ago

AmpereComputing/qwen-3-a3b-30b-thinking-gguf

31B • Updated 3 days ago • 107

updated a model 3 days ago

AmpereComputing/qwen-3-a3b-30b-instruct-gguf

31B • Updated 3 days ago • 27

updated a collection 3 days ago

Qwen 3

Collection

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp • 11 items • Updated 3 days ago • 2

published a model 3 days ago

AmpereComputing/qwen-3-a3b-30b-instruct-gguf

31B • Updated 3 days ago • 27

upvoted 4 collections 3 days ago

Llama 3.2

Collection

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp • 2 items • Updated 3 days ago • 2

GPT-OSS

Collection

With gpt-oss models we recommend using native mxfp4 quantization. • 2 items • Updated 3 days ago • 1

Bielik v3.0

Collection

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp • 2 items • Updated 3 days ago • 1

Qwen 3

Collection

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp • 11 items • Updated 3 days ago • 2

updated a collection 3 days ago

GPT-OSS

Collection

With gpt-oss models we recommend using native mxfp4 quantization. • 2 items • Updated 3 days ago • 1

updated a model 14 days ago

AmpereComputing/rakutenai-7b-chat-gguf

7B • Updated 14 days ago • 33

updated a collection 14 days ago

RakutenAI 7B

Collection

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp • 3 items • Updated 3 days ago

published a model 14 days ago

AmpereComputing/rakutenai-7b-chat-gguf

7B • Updated 14 days ago • 33

updated a model 14 days ago

AmpereComputing/rakutenai-7b-instruct-gguf

7B • Updated 14 days ago • 24

updated a collection 14 days ago

RakutenAI 7B

Collection

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp • 3 items • Updated 3 days ago

published a model 14 days ago

AmpereComputing/rakutenai-7b-instruct-gguf

7B • Updated 14 days ago • 24

updated a model 14 days ago

AmpereComputing/rakutenai-7b-gguf

7B • Updated 14 days ago • 25