Qwen · fine-tune of Qwen/Qwen2.5-14B
Qwen2.5-14B-Instruct-1M
Runs on your machine
Choose a machine
We then show the largest format that fits, from real file sizes where we have them.
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
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.
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-1M), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
weights context cache runtime
GGUF for llama.cpp, Ollama, LM Studio and others
lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF (converted by lmstudio-community), 7.3k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Memory | Get it |
|---|---|---|---|---|
| Q3_K_L | 7.4 GBfile size | 9.4 GB7.4 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF:Q3_K_LOllama ollama run hf.co/lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF:Q3_K_LDownload hf download lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF --include "Qwen2.5-14B-Instruct-1M-Q3_K_L.gguf" --local-dir Qwen2.5-14B-Instruct-1M-GGUF | |
| Q4_K_M | 8.4 GBfile size | 10.4 GB8.4 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF:Q4_K_MOllama ollama run hf.co/lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF:Q4_K_MDownload hf download lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF --include "Qwen2.5-14B-Instruct-1M-Q4_K_M.gguf" --local-dir Qwen2.5-14B-Instruct-1M-GGUF | |
| Q6_K | 11.3 GBfile size | 13.3 GB11.3 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF:Q6_KOllama ollama run hf.co/lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF:Q6_KDownload hf download lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF --include "Qwen2.5-14B-Instruct-1M-Q6_K.gguf" --local-dir Qwen2.5-14B-Instruct-1M-GGUF | |
| Q8_0 | 14.6 GBfile size | 16.6 GB14.6 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF:Q8_0Ollama ollama run hf.co/lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF:Q8_0Download hf download lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF --include "Qwen2.5-14B-Instruct-1M-Q8_0.gguf" --local-dir Qwen2.5-14B-Instruct-1M-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| MLX 4bitmlx-community/Qwen2.5-14B-Instruct-1M-4bit | 7.7 GBfile size | 9.7 GB7.7 + 1.5 + 0.50 | Download page | |
| MLX 8bitmlx-community/Qwen2.5-14B-Instruct-1M-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 | Memory | Repo |
|---|---|---|---|---|
| BF16original weights | 27.5 GBfile size | 29.5 GB27.5 + 1.5 + 0.50 |
hf download Qwen/Qwen2.5-14B-Instruct-1M --local-dir Qwen2.5-14B-Instruct-1MOther conversions (11; sizes not read)
- unsloth/Qwen2.5-14B-Instruct-1M-bnb-4bit bitsandbytes, 4bit, 133 downloads
- unsloth/Qwen2.5-14B-Instruct-1M-unsloth-bnb-4bit bitsandbytes, 4bit, 118 downloads
- graelo/Qwen2.5-14B-Instruct-1M-AWQ AWQ, 25 downloads
- cortecs/Qwen2.5-14B-Instruct-1M-FP8-Dynamic FP8, 14 downloads
- AIFunOver/Qwen2.5-14B-Instruct-1M-openvino-4bit Other, 4bit, 13 downloads
- JamAndTeaStudios/Qwen2.5-14B-Instruct-1M-FP8-Dynamic FP8, 13 downloads
- duydq12/Qwen2.5-14B-Instruct-1M-FP8-dynamic FP8, 11 downloads
- onekq-ai/Qwen2.5-14B-Instruct-1M-bnb-4bit bitsandbytes, 4bit, 7 downloads
- AIFunOver/Qwen2.5-14B-Instruct-1M-openvino-8bit Other, 8bit, 7 downloads
- divpasta123/Qwen2.5-14B-Instruct-1M-AWQ AWQ, 7 downloads
- bartowski/Qwen2.5-14B-Instruct-1M-exl2 EXL2, 6 downloads
The Hub tags 49 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.
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.