GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
cyankiwi
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
cyankiwi
Model Tree
mistralai/Ministral-3-8B-Instruct-2512
Input Modalities
Output Modalities
Supported Functionality
| Type | Ministral-3-8B-Instruct-2512-BF16 | Ministral-3-8B-Instruct-2512-AWQ-4bit |
|---|---|---|
| Memory Size | 33.2 GB | 13.4 GB |
| Benchmarks | Ministral-3-8B-Instruct-2512-BF16 | Ministral-3-8B-Instruct-2512-AWQ-4bit |
|---|---|---|
| Perplexity | 1.53717 | 1.54435 |
bash
pip install -U vllmbash
vllm serve cyankiwi/Ministral-3-8B-Instruct-2512-AWQ-4bit --tokenizer_mode mistral --config_format mistral --load_format mistral --enable-auto-tool-choice --tool-call-parser mistralA balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
This model is the instruct post-trained version in FP8, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 8B can even be deployed locally, capable of fitting in 12GB of VRAM in FP8, and less if further quantized.
Learn more in our blog post here.
Ministral 3 8B consists of two main architectural components:
The Ministral 3 8B Instruct model offers the following capabilities:
Perfect for balanced performance in local or embedded systems, combining versatility with efficiency.
Bringing advanced AI capabilities to resource-constrained environments.
We recommend deploying with the following best practices:
| Model Name | Type | Precision | Link |
|---|---|---|---|
| Ministral 3 3B Base 2512 | Base pre-trained | BF16 | Hugging Face |
| Ministral 3 3B Instruct 2512 | Instruct post-trained | FP8 | Hugging Face |
| Ministral 3 3B Reasoning 2512 | Reasoning capable | BF16 |
Other formats available here.
We compare Ministral 3 to similar sized models.
| Model | AIME25 | AIME24 | GPQA Diamond | LiveCodeBench |
|---|---|---|---|---|
| Ministral 3 14B | 0.850 | 0.898 | 0.712 | 0.646 |
| Qwen3-14B (Thinking) | 0.737 | 0.837 | 0.663 | 0.593 |
| Model | Arena Hard | WildBench | MATH Maj@1 | MM MTBench |
|---|---|---|---|---|
| Ministral 3 14B | 0.551 | 68.5 | 0.904 | 8.49 |
| Qwen3 14B (Non-Thinking) | 0.427 | 65.1 | 0.870 | NOT MULTIMODAL |
| Gemma3-12B-Instruct | 0.436 | 63.2 | 0.854 | 6.70 |
| Model | Multilingual MMLU | MATH CoT 2-Shot | AGIEval 5-shot | MMLU Redux 5-shot | MMLU 5-shot | TriviaQA 5-shot |
|---|---|---|---|---|---|---|
| Ministral 3 14B | 0.742 | 0.676 | 0.648 | 0.820 | 0.794 | 0.749 |
| Qwen3 14B Base | 0.754 | 0.620 | 0.661 | 0.837 | 0.804 |
The model can be used with the following frameworks;
vllm: See heretransformers: See hereWe recommend using this model with vLLM.
Make sure to install vllm >= 0.12.0:
text
pip install vllm --upgradeDoing so should automatically install mistral_common >= 1.8.6.
To check:
text
python -c "import mistral_common; print(mistral_common.__version__)"You can also make use of a ready-to-go docker image or on the docker hub.
Due to their size and the FP8 format of their weights Ministral-3-3B-Instruct-2512, Ministral-3-8B-Instruct-2512 and Ministral-3-14B-Instruct-2512 can run on a single 1xH200 GPU.
A simple launch command is:
bash
vllm serve mistralai/Ministral-3-8B-Instruct-2512 \ --tokenizer_mode mistral --config_format mistral --load_format mistral \ --enable-auto-tool-choice --tool-call-parser mistralKey parameter notes:
Additional flags:
--max-model-len to preserve memory. By default it is set to 262144 which is quite large but not necessary for most scenarios.--max-num-batched-tokens to balance throughput and latency, higher means higher throughput but higher latency.Here we assume that the model mistralai/Ministral-3-8B-Instruct-2512 is served and you can ping it to the domain localhost with the port 8000 which is the default for vLLM.
Let's see if the Ministral 3 knows when to pick a fight !
python
from datetime import datetime, timedelta from openai import OpenAIfrom huggingface_hub import hf_hub_download # Modify OpenAI's API key and API base to use vLLM's API server.openai_api_key = "EMPTY"openai_api_base = "http://localhost:8000/v1" TEMP = 0.15MAX_TOK = 262144 client = OpenAI( api_key=openai_api_key, base_url=openai_api_base,) models = client.models.list()model = models.data[0].id def load_system_prompt(repo_id: str, filename: str) -> str: file_path = hf_hub_download(repo_id=repo_id, filename=filename) with open(file_path, "r") as file: system_prompt = file.read() today = datetime.today().strftime("%Y-%m-%d") yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d") model_name = repo_id.split("/")[-1] return system_prompt.format(name=model_name, today=today, yesterday=yesterday) SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438" messages = [ {"role": "system", "content": SYSTEM_PROMPT}, { "role": "user", "content": [ { "type": "text", "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.", }, {"type": "image_url", "image_url": {"url": image_url}}, ], },] response = client.chat.completions.create( model=model, messages=messages, temperature=TEMP, max_tokens=MAX_TOK,) print(response.choices[0].message.content)Let's solve some equations thanks to our simple Python calculator tool.
python
import jsonfrom openai import OpenAIfrom huggingface_hub import hf_hub_download # Modify OpenAI's API key and API base to use vLLM's API server.openai_api_key = "EMPTY"openai_api_base = "http://localhost:8000/v1" TEMP = 0.15MAX_TOK = 262144 client = OpenAI( api_key=openai_api_key, base_url=openai_api_base,) models = client.models.list()model = models.data[0].id def load_system_prompt(repo_id: str, filename: str) -> str: file_path = hf_hub_download(repo_id=repo_id, filename=filename) with open(file_path, "r") as file: system_prompt = file.read() return system_prompt SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt") image_url = "https://math-coaching.com/img/fiche/46/expressions-mathematiques.jpg" def my_calculator(expression: str) -> str: return str(eval(expression)) tools = [ { "type": "function", "function": { "name": "my_calculator", "description": "A calculator that can evaluate a mathematical expression.", "parameters": { "type": "object", "properties": { "expression": { "type": "string", "description": "The mathematical expression to evaluate.", }, }, "required": ["expression"], }, }, }, { "type": "function", "function": { "name": "rewrite", "description": "Rewrite a given text for improved clarity", "parameters": { "type": "object", "properties": { "text": { "type": "string", "description": "The input text to rewrite", } }, }, }, },] messages = [ {"role": "system", "content": SYSTEM_PROMPT}, { "role": "user", "content": [ { "type": "text", "text": "Thanks to your calculator, compute the results for the equations that involve numbers displayed in the image.", }, { "type": "image_url", "image_url": { "url": image_url, }, }, ], },] response = client.chat.completions.create( model=model, messages=messages, temperature=TEMP, max_tokens=MAX_TOK, tools=tools, tool_choice="auto",) tool_calls = response.choices[0].message.tool_calls results = []for tool_call in tool_calls: function_name = tool_call.function.name function_args = tool_call.function.arguments if function_name == "my_calculator": result = my_calculator(**json.loads(function_args)) results.append(result) messages.append({"role": "assistant", "tool_calls": tool_calls})for tool_call, result in zip(tool_calls, results): messages.append( { "role": "tool", "tool_call_id": tool_call.id, "name": tool_call.function.name, "content": result, } ) response = client.chat.completions.create( model=model, messages=messages, temperature=TEMP, max_tokens=MAX_TOK,) print(response.choices[0].message.content)Ministral 3 can follow your instructions to the letter.
python
from openai import OpenAIfrom huggingface_hub import hf_hub_download # Modify OpenAI's API key and API base to use vLLM's API server.openai_api_key = "EMPTY"openai_api_base = "http://localhost:8000/v1" TEMP = 0.15MAX_TOK = 262144 client = OpenAI( api_key=openai_api_key, base_url=openai_api_base,) models = client.models.list()model = models.data[0].id def load_system_prompt(repo_id: str, filename: str) -> str: file_path = hf_hub_download(repo_id=repo_id, filename=filename) with open(file_path, "r") as file: system_prompt = file.read() return system_prompt SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt") messages = [ {"role": "system", "content": SYSTEM_PROMPT}, { "role": "user", "content": "Write me a sentence where every word starts with the next letter in the alphabet - start with 'a' and end with 'z'.", },] response = client.chat.completions.create( model=model, messages=messages, temperature=TEMP, max_tokens=MAX_TOK,) assistant_message = response.choices[0].message.contentprint(assistant_message)You can also use Ministral 3 8B Instruct 2512 with Transformers !
Transformers very recently added preliminary support for FP8, so please make sure to install from main:
sh
uv pip install git+https://github.com/huggingface/transformersTo make the best use of our model with Transformers make sure to have installed mistral-common >= 1.8.6 to use our tokenizer.
bash
pip install mistral-common --upgradeTry it out by running the following snippet.
[!Tip] By default Transformers will load the checkpoint in FP8 and dequantize it to BF16 on the fly, which means the model currently does not make use of accelerated FP8-kernels. Compatibility with accelerated FP8-kernels is currently worked on and will be available in a couple of weeks. Stay tuned!
Then load our tokenizer along with the model and generate:
python
import torchfrom transformers import Mistral3ForConditionalGeneration, MistralCommonBackend model_id = "mistralai/Ministral-3-8B-Instruct-2512" tokenizer = MistralCommonBackend.from_pretrained(model_id)model = Mistral3ForConditionalGeneration.from_pretrained(model_id, device_map="auto") image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438" messages = [ { "role": "user", "content": [ { "type": "text", "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.", }, {"type": "image_url", "image_url": {"url": image_url}}, ], },] tokenized = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True) tokenized["input_ids"] = tokenized["input_ids"].to(device="cuda")tokenized["pixel_values"] = tokenized["pixel_values"].to(dtype=torch.bfloat16, device="cuda")image_sizes = [tokenized["pixel_values"].shape[-2:]] output = model.generate( **tokenized, image_sizes=image_sizes, max_new_tokens=512,)[0] decoded_output = tokenizer.decode(output[len(tokenized["input_ids"][0]):])print(decoded_output)Note:
Transformers allows you to automatically convert the checkpoint to Bfloat16. To do so, simply load the model as follows:
py
from transformers import Mistral3ForConditionalGeneration, FineGrainedFP8Config model_id = "mistralai/Ministral-3-8B-Instruct-2512"model = Mistral3ForConditionalGeneration.from_pretrained( model_id, device_map="auto", quantization_config=FineGrainedFP8Config(dequantize=True))This model is licensed under the Apache 2.0 License.
You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.
uv pip install git+https://github.com/huggingface/transformersfrom transformers import Mistral3ForConditionalGeneration, FineGrainedFP8Config model_id = "mistralai/Ministral-3-8B-Instruct-2512"model = Mistral3ForConditionalGeneration.from_pretrained( model_id, device_map="auto", quantization_config=FineGrainedFP8Config(dequantize=True))| Ministral 3 8B Base 2512 | Base pre-trained | BF16 | Hugging Face |
| Ministral 3 8B Instruct 2512 | Instruct post-trained | FP8 | Hugging Face |
| Ministral 3 8B Reasoning 2512 | Reasoning capable | BF16 | Hugging Face |
| Ministral 3 14B Base 2512 | Base pre-trained** | BF16 | Hugging Face |
| Ministral 3 14B Instruct 2512 | Instruct post-trained | FP8 | Hugging Face |
| Ministral 3 14B Reasoning 2512 | Reasoning capable | BF16 | Hugging Face |
| Ministral 3 8B |
| 0.787 |
| 0.860 |
| 0.668 |
| 0.616 |
| Qwen3-VL-8B-Thinking | 0.798 | 0.860 | 0.671 | 0.580 |
| Ministral 3 3B | 0.721 | 0.775 | 0.534 | 0.548 |
| Qwen3-VL-4B-Thinking | 0.697 | 0.729 | 0.601 | 0.513 |
| Ministral 3 8B | 0.509 | 66.8 | 0.876 | 8.08 |
| Qwen3-VL-8B-Instruct | 0.528 | 66.3 | 0.946 | 8.00 |
| Ministral 3 3B | 0.305 | 56.8 | 0.830 | 7.83 |
| Qwen3-VL-4B-Instruct | 0.438 | 56.8 | 0.900 | 8.01 |
| Qwen3-VL-2B-Instruct | 0.163 | 42.2 | 0.786 | 6.36 |
| Gemma3-4B-Instruct | 0.318 | 49.1 | 0.759 | 5.23 |
| 0.703 |
| Gemma 3 12B Base | 0.690 | 0.487 | 0.587 | 0.766 | 0.745 | 0.788 |
| Ministral 3 8B | 0.706 | 0.626 | 0.591 | 0.793 | 0.761 | 0.681 |
| Qwen 3 8B Base | 0.700 | 0.576 | 0.596 | 0.794 | 0.760 | 0.639 |
| Ministral 3 3B | 0.652 | 0.601 | 0.511 | 0.735 | 0.707 | 0.592 |
| Qwen 3 4B Base | 0.677 | 0.405 | 0.570 | 0.759 | 0.713 | 0.530 |
| Gemma 3 4B Base | 0.516 | 0.294 | 0.430 | 0.626 | 0.589 | 0.640 |