turintech/ qwen3.5-4b-artemis:q4_k_m

27 5 hours ago

Text-only Qwen3.5 4B GGUF files. Default: q4_k_m. TurinTech models, built with Artemis.

tools thinking 
ollama run turintech/qwen3.5-4b-artemis:q4_k_m

Details

5 hours ago

3a74b7b41a69 · 2.7GB

model
qwen35
·
4.21B
·
Q4_K_M
license
Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US
params
{ "presence_penalty": 1.5, "temperature": 1, "top_k": 20, "top_p": 0.95 }

Readme

Qwen3.5 4B Artemis

Text-only GGUF versions of Qwen3.5 4B. The vision encoder and multi-token prediction (MTP) layer are not included.

TurinTech models, built with Artemis

Ollama

ollama run turintech/qwen3.5-4b-artemis:q4_k_m

latest selects q4_k_m. The explicit tags below use the same model bytes as the corresponding Hugging Face files.

Tag Hugging Face file Size
q4_k_m (default) Qwen3.5-4B-Artemis-Q4_K_M.gguf 2.714 GB
q5_k_s Qwen3.5-4B-Artemis-Q5_K_S.gguf 2.903 GB
q5_k_m Qwen3.5-4B-Artemis-Q5_K_M.gguf 3.011 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

Results vary by task and runtime. On RTX 5090, the default Q4_K_M passed 215⁄270 instruction-following prompts versus 222⁄270 for BF16. On GB10 it answered 185⁄200 tool tasks correctly versus 190⁄200 for Unsloth Q4_K_M. Original BFCL results influenced file selection, and OASST1 validation informed calibration design.

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.

The measurements on this card come from llama.cpp, not Ollama.

These files keep improving.