bvassie/qwen3-coder:30b-a3b-instruct

bvassie/ qwen3-coder:30b-a3b-instruct

23 Downloads Updated 6 days ago

Alibaba's performant long context models for agentic and coding tasks.

tools

ollama run bvassie/qwen3-coder:30b-a3b-instruct

curl http://localhost:11434/api/chat \
  -d '{
    "model": "bvassie/qwen3-coder:30b-a3b-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='bvassie/qwen3-coder:30b-a3b-instruct',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'bvassie/qwen3-coder:30b-a3b-instruct',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 6 days ago

6 days ago

c37986dce798 · 19GB ·

model

archqwen3moe

parameters30.5B

quantizationQ4_K_M

19GB

template

13B

params

{ "repeat_penalty": 1.05, "stop": [ "<|im_start|>", "<|im_end|>", "<

148B

Readme

Created using:

https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF

Modelfile:

FROM ./Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf
TEMPLATE {{ .Prompt }}
RENDERER qwen3-coder
PARSER qwen3-coder
PARAMETER repeat_penalty 1.05
PARAMETER stop <|im_start|>
PARAMETER stop <|im_end|>
PARAMETER stop <|endoftext|>
PARAMETER temperature 0.7
PARAMETER top_k 20
PARAMETER top_p 0.8