This model requires Ollama v0.6.6 or later

ollama run JollyLlama/GLM-4-32B-0414-Q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "JollyLlama/GLM-4-32B-0414-Q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='JollyLlama/GLM-4-32B-0414-Q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'JollyLlama/GLM-4-32B-0414-Q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 10 months ago

10 months ago

d61b44b6a5d3 · 20GB ·

model

archglm4

parameters32.6B

quantizationQ4_K_M

20GB

params

{ "stop": [ "<|system|>", "<|user|>", "<|assistant|>" ] }

81B

template

[gMASK]<sop>{{ if .System }}<|system|> {{ .System }}{{ end }}{{ if .Prompt }}<|user|> {{ .Prompt }}{

140B

Readme

⚠️This model requires Ollama v0.6.6 or later⚠️

https://github.com/ollama/ollama/releases

⚠️This model requires Ollama v0.6.6 or later⚠️

instruct: ollama run JollyLlama/GLM-4-32B-0414-Q4_K_M

reasoning: ollama run JollyLlama/GLM-Z1-32B-0414-Q4_K_M

Thanks to matteo for uploading the fixed gguf to HF

https://huggingface.co/matteogeniaccio