adrienbrault/
phi3-medium-128k

320 1 year ago

bartowski/Phi-3-medium-128k-instruct-GGUF

Models

View all →

12 models

phi3-medium-128k:q2_K

5.1GB · 4K context window · Text · 1 year ago

phi3-medium-128k:q3_K_S

6.1GB · 4K context window · Text · 1 year ago

phi3-medium-128k:q3_K_M

6.9GB · 4K context window · Text · 1 year ago

phi3-medium-128k:q3_K_L

7.5GB · 4K context window · Text · 1 year ago

phi3-medium-128k:q4_K_S

8.0GB · 4K context window · Text · 1 year ago

phi3-medium-128k:q4_K_M

8.6GB · 4K context window · Text · 1 year ago

phi3-medium-128k:q5_K_S

9.6GB · 4K context window · Text · 1 year ago

phi3-medium-128k:q5_K_M

10GB · 4K context window · Text · 1 year ago

phi3-medium-128k:q6_K

11GB · 4K context window · Text · 1 year ago

phi3-medium-128k:q8_0

15GB · 4K context window · Text · 1 year ago

phi3-medium-128k:Iq2_XXS

3.7GB · 4K context window · Text · 1 year ago

phi3-medium-128k:Iq2_XS

4.1GB · 4K context window · Text · 1 year ago

Readme

Uploaded with https://github.com/adrienbrault/hf-gguf-to-ollama

Ollama models of bartowski/Phi-3-medium-128k-instruct-GGUF.

Does not currently work: Error: llama runner process has terminated: signal: abort trap error:done_getting_tensors: wrong number of tensors; expected 245, got 243