Qwen3.8 2.4T-A95B
Qwen3.8-2.4T-A95B is an open-weight, post-trained language model in the Qwen3.8 series for coding, professional work, research, and multi-step agent tasks. It requires thinking mode for every interaction, with adjustable reasoning depth. Summary written by AI Index from Alibaba Qwen’s own pages.
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Tool use
- Structured output
- Open weights
Prices
2 offerings · prices as listedqwen3.8-2.4t-a95b| Conditions/ 1M tokens | Input | Cache write | Output |
|---|---|---|---|
| Standard | $2.00 | — | $6.00 |
| Explicit cache | — | $2.50 | — |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 9, 2026) · qwen3.8-2.4t-a95b model (opens in a new tab) (checked Nov 8, 2026)
qwen3.8-2.4t-a95b| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | ¥12.00 | ¥36.00 |
Prices from 阿里云百炼:模型价格 (opens in a new tab) (checked Nov 9, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Max thinking budget
- 131.07K
- Built-in tools
- Web search
- Licence
- qwen3.8-max
- Family
- qwen
- Model ID
Not stated on Alibaba Qwen’s pages: reasoning efforts, reasoning can be off, knowledge cutoff, aliases.
Run locally
Weights: Qwen/Qwen3.8-2.4T-A95B- Parameters 2.45T
- Active 95B · 512 experts, 10 per token
- Native precision BF16
- Layers 92
- KV cache per token 92 KB
- Native context 256K (model card)
- Config positions 256K (config.json max_position_embeddings)
- API context 977K (maker’s API)
- Needs
- ≈ 1271.5 GB (weights 1210.3 + KV cache 0.7 + overhead 60.5)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native) | 4556.4 GB | ≈ 4784.9 | ✕Doesn’t fit | — |
| Q8_0 | 2420.6 GB | ≈ 2542.3 | ✕Doesn’t fit | — |
| FP8 | 2278.2 GB | ≈ 2392.8 | ✕Doesn’t fit | — |
| Q6_K | 1871.0 GB | ≈ 1965.2 | ✕Doesn’t fit | — |
| Q5_K_M | 1620.4 GB | ≈ 1702.1 | ✕Doesn’t fit | — |
| Q5_0 | 1566.3 GB | ≈ 1645.3 | ✕Doesn’t fit | — |
| Q4_K_M | 1384.0 GB | ≈ 1453.9 | ✕Doesn’t fit | — |
| Q4_0 | 1281.5 GB | ≈ 1346.3 | ✕Doesn’t fit | — |
| IQ4_XS | 1210.3 GB | ≈ 1271.5 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 1113.5 GB | ≈ 1169.9 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 871.4 GB | ≈ 915.7 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 854.3 GB | ≈ 897.8 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 586.6 GB | ≈ 616.7 | ✕Doesn’t fit | — |
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): no single listed machine; about 21 × 80 GB GPUs.
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 2026-11-21. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- EQ-Bench Creative Writing v3 1,844
#18 of 95 listed models
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 28, 2026
- changes we made
Changes
All changes →No changes recorded yet.
Sources
- 阿里云百炼:模型价格in Chinese (opens in a new tab) help.aliyun.com · checked Nov 9, 2026
- Alibaba Cloud Model Studio: newly released models (opens in a new tab) alibabacloud.com · checked Nov 9, 2026
- qwen3.8-2.4t-a95b model (opens in a new tab) alibabacloud.com · checked Nov 8, 2026
- qwen3.8-2.4t-a95b (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Nov 5, 2026
- Qwen/Qwen3.8-2.4T-A95B model card (opens in a new tab) huggingface.co · checked Nov 6, 2026
- Qwen/Qwen3.8-2.4T-A95B config.json (opens in a new tab) huggingface.co · checked Nov 7, 2026
- Qwen/Qwen3.8-2.4T-A95B README.md (opens in a new tab) huggingface.co · checked Nov 4, 2026
- models.dev: alibaba/qwen3.8-2.4t-a95b (community data, MIT) (opens in a new tab) github.com · checked Oct 18, 2026
- Alibaba Cloud Model Studio pricing (opens in a new tab) alibabacloud.com · checked Nov 9, 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