Ampere Computing

company

Verified

https://amperecomputing.com/developers/power-your-ai

amperecomputing

AmpereComputingAI

Activity Feed Request to join this org

AI & ML interests

AI inference, AI in the cloud, AI on edge, software acceleration of AI workloads on hardware, efficient AI deployments, GPU-Free AI inference, AI model optimization.

Recent Activity

jangrzybek updated a collection about 2 months ago

jangrzybek updated a model about 2 months ago

AmpereComputing/gpt-oss-20b-gguf

jangrzybek published a model about 2 months ago

AmpereComputing/gpt-oss-20b-gguf

View all activity

jangrzybek

updated a collection about 2 months ago

GPT-OSS

With gpt-oss models we recommend using native mxfp4 quantization. • 3 items • Updated Sep 26 • 1

jangrzybek

updated a model about 2 months ago

AmpereComputing/gpt-oss-20b-gguf

21B • Updated Sep 26 • 44

jangrzybek

published a model about 2 months ago

AmpereComputing/gpt-oss-20b-gguf

21B • Updated Sep 26 • 44

jangrzybek

updated 4 models 2 months ago

AmpereComputing/gemma-3-27b-it-gguf

27B • Updated Sep 16 • 70

AmpereComputing/gemma-3-12b-it-gguf

12B • Updated Sep 16 • 32

AmpereComputing/gemma-3-4b-it-gguf

4B • Updated Sep 16 • 33

AmpereComputing/qwen-2.5-vl-3b-instruct-gguf

3B • Updated Sep 16 • 49

jangrzybek

updated a collection 2 months ago

Qwen 2.5

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp • 8 items • Updated Sep 16

jangrzybek

published a model 2 months ago

AmpereComputing/qwen-2.5-vl-3b-instruct-gguf

3B • Updated Sep 16 • 49

jangrzybek

updated a model 2 months ago

AmpereComputing/qwen-2.5-vl-7b-instruct-gguf

8B • Updated Sep 16 • 16

jangrzybek

updated a collection 2 months ago

Qwen 2.5

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp • 8 items • Updated Sep 16

jangrzybek

published a model 2 months ago

AmpereComputing/qwen-2.5-vl-7b-instruct-gguf

8B • Updated Sep 16 • 16

jangrzybek

updated a model 2 months ago

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

31B • Updated Sep 15 • 42

jangrzybek

updated a collection 2 months ago

Qwen 3

Ampere's quantization formats (Q4_K_4 / Q8R16) require Ampere optimized llama.cpp available here: https://hub.docker.com/r/amperecomputingai/llama.cpp • 14 items • Updated Sep 15 • 2

jangrzybek

published a model 2 months ago

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

31B • Updated Sep 15 • 42

jangrzybek

updated a model 2 months ago

AmpereComputing/deepseek-v3.1-gguf

671B • Updated Sep 13 • 17

jangrzybek

published a model 2 months ago

AmpereComputing/deepseek-v3.1-gguf

671B • Updated Sep 13 • 17

jangrzybek

updated a model 2 months ago

AmpereComputing/glm-4.5-air-gguf

110B • Updated Sep 11 • 7 • 1

jangrzybek

published a model 2 months ago

AmpereComputing/glm-4.5-air-gguf

110B • Updated Sep 11 • 7 • 1

jangrzybek

updated a model 2 months ago

AmpereComputing/ernie-4.5-a3b-21b-thinking-gguf

22B • Updated Sep 11 • 5