Instructions to use local-inference-lab/GLM-5.3-Flash-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use local-inference-lab/GLM-5.3-Flash-NVFP4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="local-inference-lab/GLM-5.3-Flash-NVFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("local-inference-lab/GLM-5.3-Flash-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("local-inference-lab/GLM-5.3-Flash-NVFP4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use local-inference-lab/GLM-5.3-Flash-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "local-inference-lab/GLM-5.3-Flash-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "local-inference-lab/GLM-5.3-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/local-inference-lab/GLM-5.3-Flash-NVFP4

SGLang

How to use local-inference-lab/GLM-5.3-Flash-NVFP4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "local-inference-lab/GLM-5.3-Flash-NVFP4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "local-inference-lab/GLM-5.3-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "local-inference-lab/GLM-5.3-Flash-NVFP4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "local-inference-lab/GLM-5.3-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use local-inference-lab/GLM-5.3-Flash-NVFP4 with Docker Model Runner:
```
docker model run hf.co/local-inference-lab/GLM-5.3-Flash-NVFP4
```

festr2 commited on Sep 4

Commit

2c62748

verified ·

1 Parent(s): 9c71213

Sync GLM-5.3 tool-result chat template

Browse files

Synchronize chat_template.jinja with zai-org/GLM-5.3-Flash revision 690b705278a3a58e538fcb37c2ca8b5f9511213c. The template preserves assistant tool-call order when serializing tool results, stops invalid reorder scans as soon as their invariant fails, uses Jinja string concatenation consistently, and handles absent message content explicitly. Model weights, tokenizer files, and serving configuration are unchanged.

Files changed (1) hide show

chat_template.jinja +10 -6

chat_template.jinja CHANGED Viewed

@@ -68,8 +68,8 @@ For each function call, output the function name and arguments within the follow
                 {{- emit_audio() -}}
             {%- endif -%}
         {%- endfor -%}
-    {%- else -%}
-        {{- content }}
     {%- endif -%}
 {%- endmacro -%}
 {%- macro tool_response(text) -%}
@@ -159,7 +159,7 @@ For each function call, output the function name and arguments within the follow
 {%- if tc.function %}
     {%- set tc = tc.function %}
 {%- endif %}
-{{- '<tool_call>' + tc.name -}}
 {% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
 {% endif %}
 {%- elif m.role == 'tool' -%}
@@ -183,9 +183,11 @@ For each function call, output the function name and arguments within the follow
         {%- set ns_chk.can_sort = false -%}
     {%- else -%}
         {%- for k in range(block_start, ns_blk.end + 1) -%}
             {%- set m = messages[k] -%}
             {%- if is_list_of_outputs(m) -%}
                 {%- for entry in m.content -%}
                     {%- set eid = id_of(entry) -%}
                     {%- if not eid -%}
                         {%- set ns_chk.can_sort = false -%}
@@ -207,6 +209,7 @@ For each function call, output the function name and arguments within the follow
             {%- endif -%}
         {%- endfor -%}
         {%- for i in range(ns_a.tool_calls | length) -%}
             {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}
             {%- if not tc_id -%}
                 {%- set ns_chk.can_sort = false -%}
@@ -214,9 +217,10 @@ For each function call, output the function name and arguments within the follow
             {%- for j in range(i + 1, ns_a.tool_calls | length) -%}
                 {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}
                     {%- set ns_chk.can_sort = false -%}
                 {%- endif -%}
             {%- endfor -%}
-    {%- endfor -%}
     {%- endif -%}
     {%- if ns_chk.can_sort -%}
         {%- for tc in ns_a.tool_calls -%}
@@ -233,8 +237,8 @@ For each function call, output the function name and arguments within the follow
                                 {{- tool_response(visible_text(entry.output)) -}}
                             {%- endif -%}
                         {%- endif -%}
-    {%- endfor -%}
-{%- else -%}
                     {%- set tk_id = id_of(m) -%}
                     {%- if tk_id == tc_id -%}
                         {{- render_tool_response(m) -}}

                 {{- emit_audio() -}}
             {%- endif -%}
         {%- endfor -%}
+    {%- elif content is not none -%}
+        {{- content -}}
     {%- endif -%}
 {%- endmacro -%}
 {%- macro tool_response(text) -%}
 {%- if tc.function %}
     {%- set tc = tc.function %}
 {%- endif %}
+{{- '<tool_call>' ~ tc.name -}}
 {% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
 {% endif %}
 {%- elif m.role == 'tool' -%}
         {%- set ns_chk.can_sort = false -%}
     {%- else -%}
         {%- for k in range(block_start, ns_blk.end + 1) -%}
+            {%- if not ns_chk.can_sort -%}{%- break -%}{%- endif -%}
             {%- set m = messages[k] -%}
             {%- if is_list_of_outputs(m) -%}
                 {%- for entry in m.content -%}
+                    {%- if not ns_chk.can_sort -%}{%- break -%}{%- endif -%}
                     {%- set eid = id_of(entry) -%}
                     {%- if not eid -%}
                         {%- set ns_chk.can_sort = false -%}
             {%- endif -%}
         {%- endfor -%}
         {%- for i in range(ns_a.tool_calls | length) -%}
+            {%- if not ns_chk.can_sort -%}{%- break -%}{%- endif -%}
             {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}
             {%- if not tc_id -%}
                 {%- set ns_chk.can_sort = false -%}
             {%- for j in range(i + 1, ns_a.tool_calls | length) -%}
                 {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}
                     {%- set ns_chk.can_sort = false -%}
+                    {%- break -%}
                 {%- endif -%}
             {%- endfor -%}
+        {%- endfor -%}
     {%- endif -%}
     {%- if ns_chk.can_sort -%}
         {%- for tc in ns_a.tool_calls -%}
                                 {{- tool_response(visible_text(entry.output)) -}}
                             {%- endif -%}
                         {%- endif -%}
+                    {%- endfor -%}
+                {%- else -%}
                     {%- set tk_id = id_of(m) -%}
                     {%- if tk_id == tc_id -%}
                         {{- render_tool_response(m) -}}