aevgeniou/qwen-cline

aevgeniou/ qwen-cline

15 Downloads Updated 2 months ago

tools

ollama run aevgeniou/qwen-cline

curl http://localhost:11434/api/chat \
  -d '{
    "model": "aevgeniou/qwen-cline",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='aevgeniou/qwen-cline',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'aevgeniou/qwen-cline',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model aevgeniou/qwen-cline

OpenCode

OpenCode ollama launch opencode --model aevgeniou/qwen-cline

Hermes Agent

Hermes Agent ollama launch hermes --model aevgeniou/qwen-cline

OpenClaw

OpenClaw ollama launch openclaw --model aevgeniou/qwen-cline

Models

Name

3 models

Size / Usage

Context

Input

qwen-cline:latest

1.9GB · 32K context window · Text · 2 months ago

qwen-cline:latest

1.9GB

32K

Text

qwen-cline:8k

1.9GB · 32K context window · Text · 2 months ago

qwen-cline:8k

1.9GB

32K

Text

qwen-cline:16k

1.9GB · 32K context window · Text · 2 months ago

qwen-cline:16k

1.9GB

32K

Text

Readme

Qwen2.5-Coder-3B-Instruct (Q4_K_M) with lowered-temperature defaults for more deterministic code generation. Weights are unmodified.

Tags

Tag	num_ctx
`:16k`	16384	same as `:latest`
`:8k`	8192	lower memory footprint
`:latest`	16384	default

All tags share identical weights and differ only in num_ctx. Common to every tag: num_keep 24 · temperature 0.2 · top_p 0.9.

You do not strictly need the :8k tag — num_ctx is overridable at runtime with /set parameter num_ctx 8192, or via the options field in an API call. The tag exists as a convenience preset.

Note that Ollama’s model table reports 32K context for every tag; that is the architecture’s maximum, not the tag’s num_ctx default.

⚠️ Not an agentic model. Despite the “-cline” name, 3B cannot reliably hold tool-call protocols — use it for chat and code completion, not as an autonomous coding agent.

License

Built with Qwen. Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright © Alibaba Cloud. All Rights Reserved. NON-COMMERCIAL USE ONLY (research or evaluation). Commercial use requires a separate license from Alibaba Cloud.

Qwen2.5-Coder-3B-Instruct (Q4_K_M) with lowered-temperature defaults for more deterministic code generation. Weights are unmodified.

## Tags

| Tag | num_ctx | |
|---|---|---|
| `:16k` | 16384 | same as `:latest` |
| `:8k` | 8192 | lower memory footprint |
| `:latest` | 16384 | default |

All tags share identical weights and differ only in `num_ctx`. Common to every tag: `num_keep 24 · temperature 0.2 · top_p 0.9`.

You do not strictly need the `:8k` tag — `num_ctx` is overridable at runtime with `/set parameter num_ctx 8192`, or via the `options` field in an API call. The tag exists as a convenience preset.

Note that Ollama's model table reports 32K context for every tag; that is the architecture's maximum, not the tag's `num_ctx` default.

⚠️ Not an agentic model. Despite the "-cline" name, 3B cannot reliably hold tool-call protocols — use it for chat and code completion, not as an autonomous coding agent.

## License

Built with Qwen. Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved. NON-COMMERCIAL USE ONLY (research or evaluation). Commercial use requires a separate license from Alibaba Cloud.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)