From 49d54ad5b480dfc81148985532797119e0e41818 Mon Sep 17 00:00:00 2001
From: Dariusz Trawinski <Dariusz.Trawinski@intel.com>
Date: Tue, 3 Mar 2026 00:08:43 +0100
Subject: [PATCH 1/2] update hf pull doc

---
 docs/pull_optimum_cli.md | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/docs/pull_optimum_cli.md b/docs/pull_optimum_cli.md
index 181841bdaa..6987d571ab 100644
--- a/docs/pull_optimum_cli.md
+++ b/docs/pull_optimum_cli.md
@@ -32,7 +32,7 @@ Using `--pull` parameter, we can use OVMS to download the model, quantize and co
 **Required:** Docker Engine installed
 
 ```text
-docker run $(id -u):$(id -g) --rm -v <model_repository_path>:/models:rw openvino/model_server:latest-py --pull --source_model <model_name_in_HF> --model_repository_path /models --model_name <external_model_name> --target_device <DEVICE> --weight-format int8 --task <task> [TASK_SPECIFIC_PARAMETERS]
+docker run -u $(id -u):$(id -g) --rm -v <model_repository_path>:/models:rw openvino/model_server:latest-py --pull --source_model <model_name_in_HF> --model_repository_path /models --model_name <external_model_name> --target_device <DEVICE> --weight-format int8 --task <task> [TASK_SPECIFIC_PARAMETERS]
 ```
 :::
 
@@ -54,8 +54,9 @@ ovms --pull --source_model "Qwen/Qwen3-8B" --model_repository_path /models --mod
 :sync: docker
 **Required:** Docker Engine installed
 
-```text
-docker run $(id -u):$(id -g) --rm -v <model_repository_path>:/models:rw openvino/model_server:latest-py --pull --source_model "Qwen/Qwen3-8B" --model_repository_path /models --model_name Qwen3-8B --task text_generation --weight-format int8
+```bash
+mkdir -p models
+docker run -u $(id -u):$(id -g) --rm -v $(pwd)/models:/models:rw openvino/model_server:latest-py --pull --source_model "Qwen/Qwen3-4B" --model_repository_path /models --model_name Qwen3-4B --task text_generation --weight-format int8
 ```
 :::
 

From bb72c1a9488b73775a11703a8eecf08135cc6e5c Mon Sep 17 00:00:00 2001
From: Dariusz Trawinski <Dariusz.Trawinski@intel.com>
Date: Tue, 3 Mar 2026 14:50:28 +0100
Subject: [PATCH 2/2] smaller models

---
 docs/pull_optimum_cli.md | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/docs/pull_optimum_cli.md b/docs/pull_optimum_cli.md
index 6987d571ab..0c046d3932 100644
--- a/docs/pull_optimum_cli.md
+++ b/docs/pull_optimum_cli.md
@@ -44,10 +44,10 @@ ovms --pull --source_model <model_name_in_HF> --model_repository_path <model_rep
 :::
 ::::
 
-Example for pulling `Qwen/Qwen3-8B`:
+Example for pulling `Qwen/Qwen3-4B`:
 
 ```bat
-ovms --pull --source_model "Qwen/Qwen3-8B" --model_repository_path /models --model_name Qwen3-8B --target_device CPU --task text_generation --weight-format int8 
+ovms --pull --source_model "Qwen/Qwen3-4B" --model_repository_path /models --model_name Qwen3-4B --target_device CPU --task text_generation --weight-format int8 
 ```
 ::::{tab-set}
 :::{tab-item} With Docker
@@ -65,7 +65,7 @@ docker run -u $(id -u):$(id -g) --rm -v $(pwd)/models:/models:rw openvino/model_
 **Required:** OpenVINO Model Server package - see [deployment instructions](./deploying_server_baremetal.md) for details.
 
 ```bat
-ovms --pull --source_model "Qwen/Qwen3-8B" --model_repository_path /models --model_name Qwen3-8B --task text_generation --weight-format int8
+ovms --pull --source_model "Qwen/Qwen3-4B" --model_repository_path /models --model_name Qwen3-4B --task text_generation --weight-format int8
 ```
 :::
 ::::
@@ -85,10 +85,10 @@ You can mount the HuggingFace cache to avoid downloading the original model in c
 Below is an example pull command with optimum model cache directory sharing for model download:
 
 ```bash
-docker run -v /etc/passwd:/etc/passwd -e HF_HOME=/hf_home/cache --user $(id -u):$(id -g) --group-add=$(id -g) -v ${HOME}/.cache/huggingface/:/hf_home/cache -v $(pwd)/models:/models:rw openvino/model_server:latest-py --pull --model_repository_path /models --source_model meta-llama/Meta-Llama-3-8B-Instruct --task text_generation --weight-format int8
+docker run -v /etc/passwd:/etc/passwd -e HF_HOME=/hf_home/cache --user $(id -u):$(id -g) --group-add=$(id -g) -v ${HOME}/.cache/huggingface/:/hf_home/cache -v $(pwd)/models:/models:rw openvino/model_server:latest-py --pull --model_repository_path /models --source_model meta-llama/Llama-3.2-1B-Instruct --task text_generation --weight-format int8
 ```
 
 or deploy without caching the model files with passed HF_TOKEN for authorization:
 ```bash
-docker run -p 8000:8000 -e HF_TOKEN=$HF_TOKEN openvino/model_server:latest-py --model_repository_path /tmp --source_model meta-llama/Meta-Llama-3-8B-Instruct --task text_generation --weight-format int8 --target_device CPU --rest_port 8000
+docker run -p 8000:8000 -e HF_TOKEN=$HF_TOKEN openvino/model_server:latest-py --model_repository_path /tmp --source_model meta-llama/Llama-3.2-1B-Instruct --task text_generation --weight-format int8 --target_device CPU --rest_port 8000
 ```
\ No newline at end of file