turintech/ qwen3.5-2b-artemis:q4_k_m

22 Downloads Updated 5 hours ago

Text-only Qwen3.5 2B GGUF files. Default: q5_k_m. TurinTech models, built with Artemis.

tools thinking

ollama run turintech/qwen3.5-2b-artemis:q4_k_m

curl http://localhost:11434/api/chat \
  -d '{
    "model": "turintech/qwen3.5-2b-artemis:q4_k_m",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='turintech/qwen3.5-2b-artemis:q4_k_m',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'turintech/qwen3.5-2b-artemis:q4_k_m',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 5 hours ago

5 hours ago

152c4b9cb8d9 · 1.3GB

model

archqwen35

·

parameters1.88B

·

quantizationQ4_K_M

1.3GB

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

params

{ "presence_penalty": 1.5, "temperature": 1, "top_k": 20, "top_p": 0.95 }

65B

Readme

Qwen3.5 2B Artemis

Text-only GGUF versions of Qwen3.5 2B. The vision encoder and multi-token prediction (MTP) layer are not included.

TurinTech models, built with Artemis

Ollama

ollama run turintech/qwen3.5-2b-artemis:q5_k_m

latest selects q5_k_m. The explicit tags below use the same model bytes as the corresponding Hugging Face files.

Tag	Hugging Face file	Size
`q5_k_m` (default)	`Qwen3.5-2B-Artemis-Q5_K_M.gguf`	1.395 GB
`q4_k_m`	`Qwen3.5-2B-Artemis-Q4_K_M.gguf`	1.280 GB

GB is download size, not runtime memory. Packages use Ollama’s Qwen3.5 renderer and tool parser, with temperature 1, top_k 20, top_p 0.95 and presence_penalty 1.5. The comparison benchmarks used llama.cpp with different sampling settings; these packages do not establish the same benchmark results in Ollama.

Measurements and limitations

In the RTX 5090 HumanEval+ check, Q5_K_M passed ⁷³⁄₁₆₄ tasks and Q4_K_M ⁷⁰⁄₁₆₄, versus ⁸¹⁄₁₆₄ for BF16. Unsloth Q4_K_M also scored higher on the earlier MMLU-Pro sample. The selected CodeSearchNet calibration functions still need a per-repository licence inventory; no calibration source text is included.

Full measurements and test conditions.

Licence

Apache-2.0, as released by Qwen (licence). See LICENSE and NOTICE. This is an independent TurinTech conversion, not affiliated with or endorsed by Alibaba Cloud or the Qwen team.

These files keep improving.

# Qwen3.5 2B Artemis

Text-only GGUF versions of Qwen3.5 2B. The vision encoder and multi-token prediction (MTP) layer are not included.

TurinTech models, built with Artemis

## Ollama

```bash
ollama run turintech/qwen3.5-2b-artemis:q5_k_m
```

`latest` selects `q5_k_m`. The explicit tags below use the same model bytes as the corresponding Hugging Face files.

| Tag | Hugging Face file | Size |
| --- | --- | --- |
| `q5_k_m` (default) | `Qwen3.5-2B-Artemis-Q5_K_M.gguf` | 1.395 GB |
| `q4_k_m` | `Qwen3.5-2B-Artemis-Q4_K_M.gguf` | 1.280 GB |

GB is download size, not runtime memory. Packages use Ollama's Qwen3.5 renderer and tool parser, with temperature 1, top_k 20, top_p 0.95 and presence_penalty 1.5. The comparison benchmarks used llama.cpp with different sampling settings; these packages do not establish the same benchmark results in Ollama.

## Measurements and limitations

In the RTX 5090 HumanEval+ check, Q5_K_M passed 73/164 tasks and Q4_K_M 70/164, versus 81/164 for BF16. Unsloth Q4_K_M also scored higher on the earlier MMLU-Pro sample. The selected CodeSearchNet calibration functions still need a per-repository licence inventory; no calibration source text is included.

[Full measurements and test conditions](https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF#how-it-was-tested).

## Licence

Apache-2.0, as released by Qwen ([licence](https://huggingface.co/Qwen/Qwen3.5-2B/blob/main/LICENSE)). See `LICENSE` and `NOTICE`. This is an independent TurinTech conversion, not affiliated with or endorsed by Alibaba Cloud or the Qwen team.

These files keep improving.

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