SAVRN
Search Contact SAVRN

Open-weight model · Text generation

Qwen2.5-Coder-14B-Instruct

by Qwen Qwen/Qwen2.5-Coder-14B-Instruct

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.

Parameters14.8B
Context32,768
Weights29.5 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1.8M

Runs On

What it takes to serve Qwen2.5-Coder-14B-Instruct (14.8B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 29.5 GB 35.4 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 14.8 GB 17.7 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 7.4 GB 8.9 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

SAVRN's Notes on Qwen2.5-Coder-14B-Instruct

Where does 14.8 billion parameters land in a coding stack? Qwen ships this code-specific line in six sizes from 0.5 to 32 billion, trained on 5.5 trillion tokens, and this instruct build derives from the Qwen2.5-Coder-14B base. At 16-bit you carry 29.5 GB of weights and need 35.4 GB of memory, which fits a single 192 GB MI300X at $1.85 per hour on demand with most of the card to spare, so the hardware question is concurrency, not fit.

Under Apache 2.0 a team can fine-tune this and ship the result inside a product, with notices kept and significant changes stated. Check the context you will actually get: the configuration lists 32,768 tokens as the context length and 131,072 as the sliding window, and the page cites the YaRN context extension paper, so your serving stack decides which number you see.

SAVRN Research, 2026-09-18

Model Card

By Qwen, published under apache-2.0, revision aedcc2d42b62.

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.
  • Long-context Support up to 128K tokens.

Read the full model card (760 words)

Configuration

Architecture
Qwen2ForCausalLM
Context length (tokens)
32,768
Layers
48
Hidden size
5,120
Feed-forward size
13,824
Attention heads
40
Key/value heads
8
Vocabulary size
152,064
Sliding window (tokens)
131,072
RoPE base
1e+06
Stored precision
bfloat16
Model type
qwen2

Identity and Version

Repository
Qwen/Qwen2.5-Coder-14B-Instruct
Publisher
Qwen
Task
Text generation
Modality
Text
Library
transformers
Parameters
14.8B parameters
Languages
en
Revision
aedcc2d42b622764e023cf882b6652e646b95671
First published
2024-11-06
Last updated
2025-01-12

Files and Weights

16 files, 29.6 GB in total. The weights are 6 files totalling 29.5 GB in safetensors.

Weights6 files · 29.5 GB
Configuration3 files · 48.4 KB
Tokenizer4 files · 11.5 MB
Documentation2 files · 17.7 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model-00001-of-00006.safetensorsWeights5.0 GB b14a60aa35c0
model-00002-of-00006.safetensorsWeights5.0 GB 03b8de22c48a
model-00003-of-00006.safetensorsWeights5.0 GB 97587f9d511a
model-00004-of-00006.safetensorsWeights5.0 GB ed34a7260634
model-00005-of-00006.safetensorsWeights5.0 GB 657a6388cfe5
model-00006-of-00006.safetensorsWeights4.7 GB 3dbbc07addfc
config.jsonConfiguration663 B —
generation_config.jsonConfiguration243 B —
model.safetensors.index.jsonConfiguration47.5 KB —
LICENSEDocumentation11.3 KB —
README.mdDocumentation6.4 KB —
.gitattributesRepository1.5 KB —
merges.txtTokenizer1.7 MB —
tokenizer.jsonTokenizer7.0 MB —
tokenizer_config.jsonTokenizer7.3 KB —
vocab.jsonTokenizer2.8 MB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
29.5 GB
Download from Qwen

Released by Qwen through ModelScope. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published29.5 GB
16-bit29.5 GB
8-bit14.8 GB
4-bit7.4 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Built on This Model

Compare Qwen2.5-Coder-14B-Instruct

Questions About Qwen2.5-Coder-14B-Instruct

How much GPU memory does Qwen2.5-Coder-14B-Instruct need?

About 35.4 GB at 16-bit and 8.9 GB at 4-bit: the weights (14.8B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run Qwen2.5-Coder-14B-Instruct on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use Qwen2.5-Coder-14B-Instruct commercially?

Yes. Qwen2.5-Coder-14B-Instruct is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

What is Qwen2.5-Coder-14B-Instruct's context length?

32,768 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Text generation

Qwen2.5-14B-Instruct

Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and…

Open weights apache-2.0 14.8B parameters 32,768 tokens transformers
View model

Model · Text generation

Qwen2.5-14B-Instruct-AWQ

Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and…

Open weights apache-2.0 14.8B parameters 32,768 tokens transformers
View model

Model · Text generation

Qwen2.5-Coder-14B-Instruct-AWQ

Qwen

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…

Open weights apache-2.0 14.8B parameters 32,768 tokens transformers
View model

A fast and efficient 14B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new Routing, Media, Vision, Sound, Tool call, and Robotics tags. Built on a DeepSeek R1-14B architecture with native ternary (BitNet-style) support and ready-to-run GGUF quantizations. - JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert model in RAG deployments, with the ONNX JiRack Java server as an alternative. - Benefits high quality CPU inference TQ2 on Llama.cpp and Ollama via QAT - Robotcs, Routing, Coding, Multimedia, Advanced tool calling via CMSManhattan/JiRackPrecisionTokenizer…

Open weights mit 14.8B parameters 131,072 tokens
View model

Model · Text generation

Qwen3-14B-AWQ

Qwen

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…

Open weights apache-2.0 14.8B parameters 40,960 tokens transformers
View model

Model · Text generation

Qwen3-14B

Qwen

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…

Open weights apache-2.0 14.8B parameters 40,960 tokens transformers
View model