Marketplace · Text & chat

Qwen3-4B-Instruct-2507-Q4_K_M

Call Qwen3-4B-Instruct-2507-Q4_K_M through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.06
per 1M output tokens
£1 buys about 17 million tokens (≈ 13 million words)
Hosts
1
Loaded now
1

At a glance.

  • Type: Text & chat
  • Hosts serving it now: 1 (1 with it loaded in memory)
  • Engines: llama_cpp
  • Context window: up to 262,144 tokens
  • Rentable: a whole host from £0.10 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
    model="Qwen3-4B-Instruct-2507-Q4_K_M",
    messages=[{"role": "user", "content": "Hello"}],
)

Qwen3-4B-Instruct-2507-Q4_K_M in detail.

We introduce the updated version of the **Qwen3-4B non-thinking mode**, named **Qwen3-4B-Instruct-2507**, featuring the following key enhancements:

Published by
Qwen
Parameters
4B
Format
transformers
Architecture
qwen3
Licence
Apache 2.0
Task
text generation
Library
transformers
First published
5 Aug 2025
Last updated
17 Sep 2025
Downloads (30 days)
2.6 million on Hugging Face
Likes
1,046

qwen3 text-generation

The model card

Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.

Qwen3-4B-Instruct-2507

Highlights

We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements:

  • Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.
  • Substantial gains in long-tail knowledge coverage across multiple languages.
  • Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation.
  • Enhanced capabilities in 256K long-context understanding.

Model Overview

Qwen3-4B-Instruct-2507 has the following features:

  • Type: Causal Language Models
  • Training Stage: Pretraining & Post-training
  • Number of Parameters: 4.0B
  • Number of Paramaters (Non-Embedding): 3.6B
  • Number of Layers: 36
  • Number of Attention Heads (GQA): 32 for Q and 8 for KV
  • Context Length: 262,144 natively.

NOTE: This model supports only non-thinking mode and does not generate ``` blocks in its output. Meanwhile, specifying enable_thinking=False` is no longer required.

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.

Performance

GPT-4.1-nano-2025-04-14Qwen3-30B-A3B Non-ThinkingQwen3-4B Non-ThinkingQwen3-4B-Instruct-2507
Knowledge
MMLU-Pro62.869.158.069.6
MMLU-Redux80.284.177.384.2
GPQA50.354.841.762.0
SuperGPQA32.242.232.042.8
Reasoning
AIME2522.721.619.147.4
HMMT259.712.012.131.0
ZebraLogic14.833.235.280.2
LiveBench 2024112541.559.448.463.0
Coding
LiveCodeBench v6 (25.02-25.05)31.529.026.435.1
MultiPL-E76.374.666.676.8
Aider-Polyglot9.824.413.812.9
Alignment
IFEval74.583.781.283.4
Arena-Hard v2*15.924.89.543.4
Creative Writing v372.768.153.683.5
WritingBench66.972.268.583.4
Agent
BFCL-v353.058.657.661.9
TAU1-Retail23.538.324.348.7
TAU1-Airline14.018.016.032.0
TAU2-Retail-31.628.140.4
TAU2-Airline-18.012.024.0
TAU2-Telecom-18.417.513.2
Multilingualism
MultiIF60.770.861.369.0
MMLU-ProX56.265.149.661.6
INCLUDE58.667.853.860.1
PolyMATH15.623.316.631.1

*: For reproducibility, we report the win rates evaluated by GPT-4.1.

Quickstart

The code of Qwen3 has been in the latest Hugging Face transformers and we advise you to use the latest version of transformers.

With transformers<4.51.0, you will encounter the following error:

KeyError: 'qwen3'

The following contains a code snippet illustrating how to use the model generate content based on given inputs.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen3-4B-Instruct-2507"
Read the rest of the model card

load the tokenizer and the model

tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" )

prepare the model input

prompt = "Give me a short introduction to large language model." messages = [ {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

conduct text completion

generated_ids = model.generate( **model_inputs, max_new_tokens=16384 ) output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

content = tokenizer.decode(output_ids, skip_special_tokens=True)

print("content:", content)


For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
- SGLang:

python -m sglang.launch_server --model-path Qwen/Qwen3-4B-Instruct-2507 --context-length 262144

- vLLM:

vllm serve Qwen/Qwen3-4B-Instruct-2507 --max-model-len 262144


**Note: If you encounter out-of-memory (OOM) issues, consider reducing the context length to a shorter value, such as `32,768`.**

For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.

### Agentic Use

Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.

To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.

from qwen_agent.agents import Assistant

Define LLM

llm_cfg = { 'model': 'Qwen3-4B-Instruct-2507',

Use a custom endpoint compatible with OpenAI API:

'model_server': 'http://localhost:8000/v1', # api_base 'api_key': 'EMPTY', }

Define Tools

tools = [ {'mcpServers': { # You can specify the MCP configuration file 'time': { 'command': 'uvx', 'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai'] }, "fetch": { "command": "uvx", "args": ["mcp-server-fetch"] } } }, 'code_interpreter', # Built-in tools ]

Define Agent

bot = Assistant(llm=llm_cfg, function_list=tools)

Streaming generation

messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}] for responses in bot.run(messages=messages): pass print(responses)


### Best Practices

To achieve optimal performance, we recommend the following settings:

1. **Sampling Parameters**:
   - We suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`.
   - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.

2. **Adequate Output Length**: We recommend using an output length of 16,384 tokens for most queries, which is adequate for instruct models.

3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
   - **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
   - **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`."

### Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwen3technicalreport, title={Qwen3 Technical Report}, author={Qwen Team}, year={2025}, eprint={2505.09388}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2505.09388}, }

Sources: Qwen/Qwen3-4B-Instruct-2507 on Hugging Face. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving Qwen3-4B-Instruct-2507-Q4_K_M right now
HostTierPriceMeasured speedHealthStateRent
iPhone 14 Pro Max · on-deviceL1£0.03 in · £0.06 out7 tok/s · 484 ms first token79loaded£0.10/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

Right now one machine serves Qwen3-4B-Instruct-2507-Q4_K_M. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
1
1 loaded in memory
Price to beat
£0.06
per 1M output tokens
Fastest measured
7 tok/s

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load Qwen3-4B-Instruct-2507-Q4_K_M, and the platform benchmarks it on your hardware before your first request.