alt.freeweights.qwen / Qwen2.5-Coder-1.5B-Instruct
From: Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject:

Qwen2.5-Coder-1.5B-Instruct

Date: 2026-11-15Commit: 2e1fd39Signed: 2DC28CC7B26A283B ✓

Text generation model with 1.5B parameters. Safetensors weights, 3.10 GB in all. Published by Qwen under Apache-2.0.

1.5B params3.10GBQwen2.5-Coder-1.5B-Instructsafetensorspermissive
FactsParams1.5BSize3.10 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get Qwen/Qwen2.5-Coder-1.5B-Instruct
# manifest sha256 b8988ec45383… · 3.10 GB · 10 files
$ fw verify ./Qwen2.5-Coder-1.5B-Instruct Qwen/Qwen2.5-Coder-1.5B-Instruct
From sourceHosted (signed)Qwen/Qwen2.5-Coder-1.5B-InstructLast check: 2026-11-15 02:27 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of Qwen2.5-Coder-1.5B.

Works with

Overview

Size
3.10 GB
Weights
3.09 GB (safetensors)
Parameters
1.5B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
10, each with a sha256
Publisher
Qwen
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-Coder-1.5B

Where these bytes come from
Publisher at the pinned commitโ†’You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 02:27 UTCpassed

Model card

From the publisher at commit 2e1fd39. Shown as plain text with links; images open at the publisher.

Qwen2.5-Coder-1.5B-Instruct#

Chat

Introduction#

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

  • Significantly improvements in code generation, code reasoning and code fixing. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o.
  • A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.

This repo contains the instruction-tuned 1.5B Qwen2.5-Coder model, which has the following features:

  • Type: Causal Language Models
  • Training Stage: Pretraining & Post-training
  • Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
  • Number of Parameters: 1.54B
  • Number of Paramaters (Non-Embedding): 1.31B
  • Number of Layers: 28
  • Number of Attention Heads (GQA): 12 for Q and 2 for KV
  • Context Length: Full 32,768 tokens

For more details, please refer to our blog, GitHub, Documentation, Arxiv.

Requirements#

The code of Qwen2.5-Coder has been in the latest Hugging face transformers and we advise you to use the latest version of transformers.

With transformers<4.37.0, you will encounter the following error:

KeyError: 'qwen2'

Quickstart#

Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen2.5-Coder-1.5B-Instruct"

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

prompt = "write a quick sort algorithm."
messages = [
    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
    {"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)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Evaluation & Performance#

Detailed evaluation results are reported in this ๐Ÿ“‘ blog.

For requirements on GPU memory and the respective throughput, see results here.

Citation#

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

@article{hui2024qwen2,
      title={Qwen2. 5-Coder Technical Report},
      author={Hui, Binyuan and Yang, Jian and Cui, Zeyu and Yang, Jiaxi and Liu, Dayiheng and Zhang, Lei and Liu, Tianyu and Zhang, Jiajun and Yu, Bowen and Dang, Kai and others},
      journal={arXiv preprint arXiv:2409.12186},
      year={2024}
}
@article{qwen2,
      title={Qwen2 Technical Report}, 
      author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
      journal={arXiv preprint arXiv:2407.10671},
      year={2024}
}

Files

10 files ยท 3.10 GBWeights 3.09 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 10 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
LICENSE11.3 KB832dd9e00a68dd83b3c3fb9f5588dad7dcf337a0db50f7d9483f310cd292e92e
README.md5.26 KBa8504fd3e1247c90e4fe640d84df963237134bf29db02b0de7d502eed6c93c33
config.json660 B88f9a17863c05fb313515d2ff74b1098e0c35579f99068e32beda00618508ae0
generation_config.json242 B1a628a5775bc69cde01c6749a531150ca4d3189652c618a174f7077923acf3b1
merges.txt1.67 MB599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3
model.safetensors3.09 GBc1b9b30e907950516ba3c646bdf570d8084c25a6410a0cdca80cf04b11bc13a8
tokenizer.json7.03 MBc0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539
tokenizer_config.json7.30 KB959e7f1d9a1b7641a6d6ce05ca97b75c7894fcb66cbe5a040406458fb1128ee4
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
2e1fd397ee pinned now2026-11-15 02:27 UTC10 files ยท 3.10 GB

Use it

$ fw get Qwen/Qwen2.5-Coder-1.5B-Instruct
# manifest sha256 b8988ec45383… · 3.10 GB · 10 files
$ fw verify ./Qwen2.5-Coder-1.5B-Instruct Qwen/Qwen2.5-Coder-1.5B-Instruct
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/Qwen/Qwen2.5-Coder-1.5B-Instruct.json --dir ./Qwen2.5-Coder-1.5B-Instruct $ python3 fw.py verify ./Qwen2.5-Coder-1.5B-Instruct ./Qwen__Qwen2.5-Coder-1.5B-Instruct.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Qwen/Qwen2.5-Coder-1.5B-Instruct --revision 2e1fd397ee46e1388853d2af2c993145b0f1098a --local-dir ./Qwen2.5-Coder-1.5B-Instruct
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-1.5B-Instruct", revision="2e1fd397ee46e1388853d2af2c993145b0f1098a") model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B-Instruct", revision="2e1fd397ee46e1388853d2af2c993145b0f1098a", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve Qwen/Qwen2.5-Coder-1.5B-Instruct --revision 2e1fd397ee46e1388853d2af2c993145b0f1098a

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
LICENSE
Text sha256
832dd9e00a68dd83b3c3fb9f5588dad7dcf337a0db50f7d9483f310cd292e92e
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject: Qwen2.5-Coder-1.5B-InstructDate: 2026-11-15Commit: 2e1fd39Signed: 2DC28CC7B26A283B ✓
Upstream
Qwen/Qwen2.5-Coder-1.5B-Instruct
Pinned commit
2e1fd397ee46e1388853d2af2c993145b0f1098a
Manifest
Qwen2.5-Coder-1.5B-Instruct.json ยท .minisig
Manifest sha256
b8988ec45383704fdad2e7c0a59e5c74b0529c873588c40280d84532165f5e93
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 02:27 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen2.5-Coder-1.5B-Instruct.json $ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen2.5-Coder-1.5B-Instruct.json.minisig $ minisign -Vm Qwen2.5-Coder-1.5B-Instruct.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

Qwen/Qwen2.5-Coder-1.5B ยท this model is a finetune of it

14 models in the catalog name this one as their parent.

Quantizations
14
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Qwen/Qwen2.5-Coder-1.5B-Instruct
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen2.5-Coder-1.5B-Instruct.json. Provenance. Takedown history: none.

Variants

14 quantized or adapter builds of Qwen2.5-Coder-1.5B-Instruct. Each has its own license check and page.

SubjectSizeParamsLicenseDate
Qwen2.5-Coder-1.5B-Instruct-GGUFHosted (signed) From: Qwen in alt.freeweights.qwen9.76 GBโ€”Permissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-GGUFHosted (signed) From: bartowski in alt.freeweights.qwen25.3 GBโ€”Permissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-bnb-4bitHosted (signed) From: unsloth in alt.freeweights.qwen1.15 GB1.6BPermissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-GGUFHosted (signed) From: lmstudio-community in alt.freeweights.qwen4.79 GBโ€”Permissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-128K-GGUFHosted (signed) From: unsloth in alt.freeweights.qwen9.62 GBโ€”Permissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-MLX-8bitHosted (signed) From: lmstudio-community in alt.freeweights.qwen1.66 GB1.5BPermissive2026-11-15Qwen2.5.1-Coder-1.5B-Instruct-GGUFHosted (signed) From: bartowski in alt.freeweights.qwen21.0 GBโ€”Permissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-GGUFHosted (signed) From: unsloth in alt.freeweights.qwen9.62 GBโ€”Permissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-MLX-4bitHosted (signed) From: lmstudio-community in alt.freeweights.qwen885 MB1.5BPermissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-AWQHosted (signed) From: Qwen in alt.freeweights.qwen1.63 GB1.8BPermissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-Q8_0-GGUFHosted (signed) From: ggml-org in alt.freeweights.qwen1.65 GBโ€”Permissive2026-11-15Qwen2.5-Coder-1.5B-InstructHosted (signed) From: onnx-community in alt.freeweights.qwen21.2 GBโ€”Permissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4Hosted (signed) From: Qwen in alt.freeweights.qwen1.16 GB1.5BPermissive2026-11-15Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8Hosted (signed) From: Qwen in alt.freeweights.qwen1.82 GB1.5BPermissive2026-11-15
From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF