# Qwen2.5-Coder-7B by Qwen: Open-Weight Model Source: https://savrn.com/models/qwen2-5-coder-7b Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Qwen2.5-Coder-7B (7.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 15.2 GB | 18.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 7.6 GB | 9.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 3.8 GB | 4.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026. [Qwen2.5-Coder-7B on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/qwen2-5-coder-7b/gpus) ## SAVRN's Notes on Qwen2.5-Coder-7B 18.3 GB at 16-bit, 4.6 GB at 4-bit, one MI300X at $1.85 an hour: same memory envelope as the general-purpose Qwen2.5-7B next door, because it is derived from it — 7.6B parameters, 32,768 tokens of context, four safetensors shards totaling 15.2 GB. The single-card fit at 4-bit is what keeps this size class popular for code completion and CI-adjacent tooling. Apache 2.0 permits commercial use with notices kept. The catch is in the name: this is the base Coder checkpoint, not an instruct model, so it completes code rather than answering questions about it. The Qwen2.5-Coder family runs from 0.5B to 32B, and this midpoint is the smallest size we would put on a real completion workload. No evaluations are reported on this page — rely on your own repo-level benchmarks. SAVRN Research ## Model Card By Qwen, published under apache-2.0, revision 0396a76181e1. ### 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 (684 words)](https://savrn.com/models/qwen2-5-coder-7b/card) ## Configuration Architecture Qwen2ForCausalLM Context length (tokens) 32,768 Layers 28 Hidden size 3,584 Feed-forward size 18,944 Attention heads 28 Key/value heads 4 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-7B Publisher Qwen Task Text generation Modality Text Library transformers Parameters 7.6B parameters Languages en Revision 0396a76181e127dfc13e5c5ec48a8cee09938b02 First published 2024-09-16 Last updated 2024-11-18 ## Files and Weights 14 files, 15.2 GB in total. The weights are 4 files totalling 15.2 GB in safetensors. Weights4 files · 15.2 GB Configuration3 files · 28.5 KB Tokenizer4 files · 11.5 MB Documentation2 files · 16.5 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00004.safetensors | Weights | 4.9 GB | 2296315c41cc | | model-00002-of-00004.safetensors | Weights | 4.9 GB | 9db3a8f68a41 | | model-00003-of-00004.safetensors | Weights | 4.3 GB | 292de283f4dc | | model-00004-of-00004.safetensors | Weights | 1.1 GB | 0167e1c1b01c | | config.json | Configuration | 668 B | — | | generation_config.json | Configuration | 122 B | — | | model.safetensors.index.json | Configuration | 27.8 KB | — | | LICENSE | Documentation | 11.3 KB | — | | README.md | Documentation | 5.2 KB | — | | .gitattributes | Repository | 1.5 KB | — | | merges.txt | Tokenizer | 1.7 MB | — | | tokenizer.json | Tokenizer | 7.0 MB | — | | tokenizer_config.json | Tokenizer | 7.3 KB | — | | vocab.json | Tokenizer | 2.8 MB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 15.2 GB [Download from Qwen](https://modelscope.cn/models/Qwen/Qwen2.5-Coder-7B) Released by Qwen through ModelScope. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from [Qwen/Qwen2.5-7B](https://savrn.com/models/qwen2-5-7b) - Described by [arXiv:2309.00071](https://savrn.com/papers/yarn-efficient-context-window-extension-of-large-language-models) - Described by [arXiv:2407.10671](https://savrn.com/papers/qwen2-technical-report) - Described by [arXiv:2409.12186](https://savrn.com/papers/qwen2-5-coder-technical-report) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 15.2 GB | | 16-bit | 15.2 GB | | 8-bit | 7.6 GB | | 4-bit | 3.8 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Derived from[Qwen2.5-Coder-7B-Instruct](https://savrn.com/models/qwen2-5-coder-7b-instruct) ## Compare Qwen2.5-Coder-7B - [Qwen2.5-7B-Instruct vs Qwen2.5-Coder-7B](https://savrn.com/models/compare/qwen2-5-7b-instruct-vs-qwen2-5-coder-7b) ## Questions About Qwen2.5-Coder-7B ### How much GPU memory does Qwen2.5-Coder-7B need? About 18.3 GB at 16-bit and 4.6 GB at 4-bit: the weights (7.6B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run Qwen2.5-Coder-7B 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-7B commercially? Yes. Qwen2.5-Coder-7B 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-7B's context length? 32,768 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [Qwen2.5-7B-Instruct](https://savrn.com/models/qwen2-5-7b-instruct) [Qwen](https://savrn.com/model-publishers/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 7.6B parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen2-5-7b-instruct) Model · Text generation ### [Qwen2.5-7B-Instruct-AWQ](https://savrn.com/models/qwen2-5-7b-instruct-awq) [Qwen](https://savrn.com/model-publishers/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 7.6B parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen2-5-7b-instruct-awq) Model · Text generation ### [Qwen2.5-Coder-7B-Instruct](https://savrn.com/models/qwen2-5-coder-7b-instruct) [Qwen](https://savrn.com/model-publishers/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 7.6B parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen2-5-coder-7b-instruct) Model · Text generation ### [Qwen2.5-Coder-7B-Instruct-AWQ](https://savrn.com/models/qwen2-5-coder-7b-instruct-awq) [Qwen](https://savrn.com/model-publishers/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 7.6B parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen2-5-coder-7b-instruct-awq) Model · Text generation ### [Qwen2.5-7B](https://savrn.com/models/qwen2-5-7b) [Qwen](https://savrn.com/model-publishers/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 7.6B parameters 131,072 tokens transformers [View model](https://savrn.com/models/qwen2-5-7b) Model · Text generation ### [JiRackUltra_7b](https://savrn.com/models/jirackultra-7b) [Center Business Solutions inc](https://savrn.com/model-publishers/cmsmanhattan) A fast and efficient 7B 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 -7B 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 7.6B parameters 131,072 tokens [View model](https://savrn.com/models/jirackultra-7b) ## Qwen [All models and datasets](https://savrn.com/model-publishers/qwen) ## Versions - [0396a76181e1](https://savrn.com/models/qwen2-5-coder-7b/versions/0396a76181e1) · current 2026-09-18 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [Qwen website](https://qwen.ai/) - [Hugging Face record](https://huggingface.co/Qwen/Qwen2.5-Coder-7B) - [How the hub is built](https://savrn.com/model-hub/methodology)