- Size
- 14.8B parameterscounted from the safetensors header on the Hub
- Licence
- custom, read it, Apache License 2.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
- On the Hub since
- 16 Sep 2024the date the repo was created
- Context length
- 32k tokensfrom the model's config
- Fine-tune
- of Qwen/Qwen2.5-14BQwen2ForCausalLM
- On Hugging Face
- Qwen/Qwen2.5-14B-Instruct574k downloads in the last 30 days, 384 likes
Scores
- Shots: 579.9%Phi-4 Technical Report
Epoch's name: qwen2.5-14b-instruct. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 1.5 GB, worked out from the model's config (Qwen/Qwen2.5-14B-Instruct), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
Qwen/Qwen2.5-14B-Instruct-GGUF (the maker's own conversion), 49k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 5.4 GBfile size, 2 parts | 7.4 GB5.4 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-14B-Instruct-GGUF:Q2_KDownload hf download Qwen/Qwen2.5-14B-Instruct-GGUF --include "qwen2.5-14b-instruct-q2_k-*-of-00002.gguf" --local-dir Qwen2.5-14B-Instruct-GGUF |
| Q3_K_M | 6.8 GBfile size, 2 parts | 8.8 GB6.8 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-14B-Instruct-GGUF:Q3_K_MDownload hf download Qwen/Qwen2.5-14B-Instruct-GGUF --include "qwen2.5-14b-instruct-q3_k_m-*-of-00002.gguf" --local-dir Qwen2.5-14B-Instruct-GGUF |
| Q4_0 | 7.9 GBfile size, 3 parts | 9.9 GB7.9 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-14B-Instruct-GGUF:Q4_0Download hf download Qwen/Qwen2.5-14B-Instruct-GGUF --include "qwen2.5-14b-instruct-q4_0-*-of-00003.gguf" --local-dir Qwen2.5-14B-Instruct-GGUF |
| Q4_K_M | 8.4 GBfile size, 3 parts | 10.4 GB8.4 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-14B-Instruct-GGUF:Q4_K_MDownload hf download Qwen/Qwen2.5-14B-Instruct-GGUF --include "qwen2.5-14b-instruct-q4_k_m-*-of-00003.gguf" --local-dir Qwen2.5-14B-Instruct-GGUF |
| Q5_0 | 9.6 GBfile size, 3 parts | 11.6 GB9.6 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-14B-Instruct-GGUF:Q5_0Download hf download Qwen/Qwen2.5-14B-Instruct-GGUF --include "qwen2.5-14b-instruct-q5_0-*-of-00003.gguf" --local-dir Qwen2.5-14B-Instruct-GGUF |
| Q5_K_M | 9.8 GBfile size, 3 parts | 11.8 GB9.8 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-14B-Instruct-GGUF:Q5_K_MDownload hf download Qwen/Qwen2.5-14B-Instruct-GGUF --include "qwen2.5-14b-instruct-q5_k_m-*-of-00003.gguf" --local-dir Qwen2.5-14B-Instruct-GGUF |
| Q6_K | 11.3 GBfile size, 4 parts | 13.3 GB11.3 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-14B-Instruct-GGUF:Q6_KDownload hf download Qwen/Qwen2.5-14B-Instruct-GGUF --include "qwen2.5-14b-instruct-q6_k-*-of-00004.gguf" --local-dir Qwen2.5-14B-Instruct-GGUF |
| Q8_0 | 14.6 GBfile size, 4 parts | 16.6 GB14.6 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-14B-Instruct-GGUF:Q8_0Download hf download Qwen/Qwen2.5-14B-Instruct-GGUF --include "qwen2.5-14b-instruct-q8_0-*-of-00004.gguf" --local-dir Qwen2.5-14B-Instruct-GGUF |
| F16 | 27.5 GBfile size, 8 parts | 29.5 GB27.5 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-14B-Instruct-GGUF:F16Download hf download Qwen/Qwen2.5-14B-Instruct-GGUF --include "qwen2.5-14b-instruct-fp16-*-of-00008.gguf" --local-dir Qwen2.5-14B-Instruct-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitlmstudio-community/Qwen2.5-14B-Instruct-MLX-4bit | 7.7 GBfile size | 9.7 GB7.7 + 1.5 + 0.50 | Download page |
| MLX 8bitlmstudio-community/Qwen2.5-14B-Instruct-MLX-8bit | 14.6 GBfile size | 16.6 GB14.6 + 1.5 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 27.5 GBfile size | 29.5 GB27.5 + 1.5 + 0.50 |
hf download Qwen/Qwen2.5-14B-Instruct --local-dir Qwen2.5-14B-InstructOther conversions (14; sizes not read)
- Qwen/Qwen2.5-14B-Instruct-AWQ AWQ, by the maker, 1.0M downloads
- Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4 GPTQ, int4, by the maker, 14k downloads
- Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8 GPTQ, int8, by the maker, 2.7k downloads
- unsloth/Qwen2.5-14B-Instruct-bnb-4bit bitsandbytes, 4bit, 23k downloads
- unsloth/Qwen2.5-14B-Instruct-unsloth-bnb-4bit bitsandbytes, 4bit, 11k downloads
- amd/Qwen2.5-14B-Instruct_gpuep_1.0_gpu_128 Other, 246 downloads
- RedHatAI/Qwen2.5-14B-Instruct-quantized.w8a8 Other, w8a8, 148 downloads
- OpenVINO/Qwen2.5-14B-Instruct-int4-ov Other, int4, 143 downloads
- Xylolabs/Qwen2.5-14B-Instruct-Tenstorrent-Tensix-BFP4-QKV8-Down8 Other, 83 downloads
- turboderp/Qwen2.5-14B-Instruct-exl3 EXL3, 50 downloads
- divaspoudel/iol-Qwen2.5-14B-Instruct-AWQ AWQ, 49 downloads
- gneupane/iol-Qwen2.5-14B-Instruct-AWQ AWQ, 36 downloads
- osllmai-community/Qwen2.5-14B-Instruct-bnb-4bit bitsandbytes, 4bit, 25 downloads
- JongYeop/Qwen2.5-14B-Instruct-FP4-W4A4 NVFP4, 25 downloads
The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- unsloth/Qwen2.5-14B-Instruct14.8B74kUnreviewed
- nvidia/OpenCodeReasoning-Nemotron-14B14.8B783Unreviewed
- nvidia/OpenCodeReasoning-Nemotron-1.1-14B14.8B252Unreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.