Qwen2.5-14B-Instruct-1M
- Tool use
- Structured output
- Open weights
Prices
1 offering · prices as listedqwen2.5-14b-instruct-1m| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard no longer listed since Oct 1, 2026 past price, from the vendor’s page archived Jan 16, 2026 | $0.805 | $3.22 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Sep 30, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Reasoning
- —
- Family
- qwen
- Model ID
Not stated on Alibaba Qwen’s pages: max input, input modalities, output modalities, reasoning efforts, reasoning can be off, max thinking budget, built-in tools, knowledge cutoff, licence, aliases.
Run locally
Weights: Qwen/Qwen2.5-14B-Instruct-1M- Parameters 14.8B
- Dense
- Native precision BF16
- Layers 48
- KV cache per token 192 KB
- Config positions 986K (config.json max_position_embeddings)
- API context 977K (maker’s API)
- Needs
- ≈ 16.8 GB (weights 14.6 + KV cache 1.5 + overhead 0.7)
- Usable
- 21.6 GB (90% of its memory)
- Generation speed
- 29–44 tok/s
- Longest context
- 33K (longer doesn’t fit)
- First token
- about 0.48–0.72 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 27.5 GB | ≈ 30.4 | ○Needs system memory 4–6 tok/s | — |
| Q8_0 | 14.6 GB | ≈ 16.8 | ●Runs well 29–44 tok/s | 33K |
| FP8 | 13.8 GB | ≈ 15.9 | ●Runs well 31–46 tok/s | 38K |
| Q6_K | 11.3 GB | ≈ 13.4 | ●Runs well 37–55 tok/s | 51K |
| Q5_K_M | 9.8 GB | ≈ 11.8 | ●Runs well 42–62 tok/s | 60K |
| Q5_0 | 9.5 GB | ≈ 11.5 | ●Runs well 43–64 tok/s | 62K |
| Q4_K_M | 8.4 GB | ≈ 10.4 | ●Runs well 48–71 tok/s | 68K |
| Q4_0 | 7.7 GB | ≈ 9.7 | ●Runs well 51–76 tok/s | 71K |
| IQ4_XS | 7.3 GB | ≈ 9.3 | ●Runs well 53–80 tok/s | 73K |
| Q3_K_Mquality drops | 6.7 GB | ≈ 8.7 | ●Runs well 57–86 tok/s | 76K |
| IQ3_XXSquality drops | 5.3 GB | ≈ 7.3 | ●Runs well 69–104 tok/s | 84K |
| Q2_Kquality drops | 5.2 GB | ≈ 7.2 | ●Runs well 70–106 tok/s | 85K |
| IQ2_XXSquality drops | 3.5 GB | ≈ 5.5 | ●Runs well 93–140 tok/s | 93K |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): GPU GeForce RTX 5070; unified memory Apple M5 · 16 GB.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by usThis model isn’t on any leaderboard we cite yet.
Changes
All changes →No changes recorded yet.
Sources
- Text generation models - Qwen, DeepSeek, GLM | Model Studio - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Oct 15, 2026
- Qwen2.5-14B-Instruct-1M (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Alibaba Cloud Model Studio pricing (opens in a new tab) alibabacloud.com · checked Sep 30, 2026
- Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens | Qwen (opens in a new tab) qwenlm.github.io · checked Oct 30, 2026
- Qwen/Qwen2.5-14B-Instruct-1M model card (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-14B-Instruct-1M config.json (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen2.5-14B-Instruct-1M files (opens in a new tab) huggingface.co · checked Oct 31, 2026
Alibaba Qwen’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Alibaba Qwen · China · qwen.ai
Related models
Snapshots, the same family and other models from this provider