# Qwen2.5-14B-Instruct by Qwen: Open-Weight Model Source: https://savrn.com/models/qwen2-5-14b-instruct Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Qwen2.5-14B-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. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 29.5 GB | 35.4 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 | 14.8 GB | 17.7 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 | 7.4 GB | 8.9 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 23, 2026. [Qwen2.5-14B-Instruct on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/qwen2-5-14b-instruct/gpus) ## SAVRN's Notes on Qwen2.5-14B-Instruct 14.8B parameters with a 32,768-token context and 1.8M downloads a month. Memory: 35.4 GB at 16-bit, 17.7 GB at 8-bit and 8.9 GB at 4-bit — one MI300X at $1.85 an hour fits every precision, and at 4-bit a workstation card does too. The repo is 18 files totalling 29.6 GB, with the bf16 weights in 29.5 GB of safetensors. Apache 2.0 permits commercial use with notices kept. An official AWQ build, Qwen2.5-14B-Instruct-AWQ, is listed as quantized from this checkpoint — take it if you want 8-bit-class memory without calibrating yourself. It derives from Qwen2.5-14B, described by arXiv:2309.00071 and arXiv:2407.10671, and no host on our Index prices it per token: rent by the hour or self-host. Weights were released 2024-09-16 and last updated 2024-09-25. SAVRN Research ## Model Card By Qwen, published under apache-2.0, revision cf98f3b3bbb4. ### Introduction 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 condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. [Read the full model card (753 words)](https://savrn.com/models/qwen2-5-14b-instruct/card) ## 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/Qwen2.5-14B-Instruct Publisher Qwen Task Text generation Modality Text Library transformers Parameters 14.8B parameters Languages en Revision cf98f3b3bbb457ad9e2bb7baf9a0125b6b88caa8 First published 2024-09-16 Last updated 2024-09-25 ## Files and Weights 18 files, 29.6 GB in total. The weights are 8 files totalling 29.5 GB in safetensors. Weights8 files · 29.5 GB Configuration3 files · 48.4 KB Tokenizer4 files · 11.5 MB Documentation2 files · 17.4 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00008.safetensors | Weights | 3.9 GB | b477be7572f0 | | model-00002-of-00008.safetensors | Weights | 4.0 GB | eb356aacae44 | | model-00003-of-00008.safetensors | Weights | 4.0 GB | cee9dbdf738c | | model-00004-of-00008.safetensors | Weights | 4.0 GB | b1201a6edcac | | model-00005-of-00008.safetensors | Weights | 4.0 GB | fbbda3cdee31 | | model-00006-of-00008.safetensors | Weights | 4.0 GB | f7ac652aa101 | | model-00007-of-00008.safetensors | Weights | 4.0 GB | e9115e615b57 | | model-00008-of-00008.safetensors | Weights | 1.7 GB | a77f603d8368 | | config.json | Configuration | 663 B | — | | generation_config.json | Configuration | 242 B | — | | model.safetensors.index.json | Configuration | 47.5 KB | — | | LICENSE | Documentation | 11.3 KB | — | | README.md | Documentation | 6.0 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 29.5 GB [Download from Qwen](https://modelscope.cn/models/Qwen/Qwen2.5-14B-Instruct) Released by Qwen through ModelScope. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from Qwen/Qwen2.5-14B - 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) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 29.5 GB | | 16-bit | 29.5 GB | | 8-bit | 14.8 GB | | 4-bit | 7.4 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Quantized from[Qwen2.5-14B-Instruct-AWQ](https://savrn.com/models/qwen2-5-14b-instruct-awq) - Derived from[Qwen2.5-14B-Instruct-AWQ](https://savrn.com/models/qwen2-5-14b-instruct-awq) - Derived from[qwen-text-to-sql-2026-09-26_18.29.52-Qwen2.5-14B-Instruct-finetune-QLORA](https://savrn.com/models/qwen-text-to-sql-2026-09-26-18-29-52-qwen2-5-14b-instruct-finetune-qlora) - Derived from[cacherepair](https://savrn.com/models/cacherepair) - Adapter of[theo_qwen2.5-14b-it_loyalty-dpo-lora](https://savrn.com/models/theo-qwen2-5-14b-it-loyalty-dpo-lora) - Derived from[theo_qwen2.5-14b-it_loyalty-dpo-lora](https://savrn.com/models/theo-qwen2-5-14b-it-loyalty-dpo-lora) - Quantized from[vedic-qwen2.5-14b-GGUF](https://savrn.com/models/vedic-qwen2-5-14b-gguf) - Derived from[vedic-qwen2.5-14b-GGUF](https://savrn.com/models/vedic-qwen2-5-14b-gguf) - Adapter of[OPSD-SDPO-v22-Qwen2.5-14B-checkpoints](https://savrn.com/models/opsd-sdpo-v22-qwen2-5-14b-checkpoints) - Derived from[OPSD-SDPO-v22-Qwen2.5-14B-checkpoints](https://savrn.com/models/opsd-sdpo-v22-qwen2-5-14b-checkpoints) ## Questions About Qwen2.5-14B-Instruct ### How much GPU memory does Qwen2.5-14B-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 Qwen2.5-14B-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 Qwen2.5-14B-Instruct commercially? Yes. Qwen2.5-14B-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 Qwen2.5-14B-Instruct's context length? 32,768 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [Qwen2.5-Coder-14B-Instruct](https://savrn.com/models/qwen2-5-coder-14b-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 14.8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen2-5-coder-14b-instruct) Model · Text generation ### [Qwen2.5-14B-Instruct-AWQ](https://savrn.com/models/qwen2-5-14b-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 14.8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen2-5-14b-instruct-awq) Model · Text generation ### [Qwen2.5-Coder-14B-Instruct-AWQ](https://savrn.com/models/qwen2-5-coder-14b-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 14.8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/qwen2-5-coder-14b-instruct-awq) Model · Text generation ### [JiRackUltra_14b](https://savrn.com/models/jirackultra-14b) [Center Business Solutions inc](https://savrn.com/model-publishers/cmsmanhattan) 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](https://savrn.com/models/jirackultra-14b) Model · Text generation ### [XiYanSQL-QwenCoder-14B-2504](https://savrn.com/models/xiyansql-qwencoder-14b-2504) [XGenerationLab](https://savrn.com/model-publishers/xgenerationlab) We are excited to release the XiYanSQL-QwenCoder-2504 version, our latest SQL generation model. This version continues to optimize upon the previous version, delivering enhanced performance. - Our model incorporates important explorations combining fine-tuning and GRPO training, leveraging the post-training strategies of GRPO without a thinking process, achieving both efficiency and accuracy in SQL generation. - It demonstrates impressive performance and supports multiple dialects, ready to use out of the box. - Improved generalization capabilities, excelling on different dialects and out-of-domain datasets. In this evaluation, we have also added a real-world SQL benchmark (the DW test… Open weights apache-2.0 14.8B parameters 32,768 tokens [View model](https://savrn.com/models/xiyansql-qwencoder-14b-2504) Model · Text generation ### [MN-12B-Celeste-V1.9-GGUF](https://savrn.com/models/mn-12b-celeste-v1-9-gguf) [Ahmed Alani](https://savrn.com/model-publishers/adking98) This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 14.8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/mn-12b-celeste-v1-9-gguf) ## Qwen [All models and datasets](https://savrn.com/model-publishers/qwen) ## Versions - [cf98f3b3bbb4](https://savrn.com/models/qwen2-5-14b-instruct/versions/cf98f3b3bbb4) · current 2026-10-18 ## 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/Qwen2.5-14B-Instruct) - [How the hub is built](https://savrn.com/model-hub/methodology)