Qwen3.5-122B-A10B
- In Input modalities: TextImageVideo Out Output modalities: Text
- Reasoning
- Reasoning can be off
- Tool use
- Structured output
- Open weights
Prices
6 offerings · prices as listedqwen3.5-122b-a10b| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.115 | $0.917 |
| Prompts over 128K tokens | $0.287 | $2.294 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 2, 2026)
qwen3.5-122b-a10b| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.40 | $3.20 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 2, 2026)
qwen3.5-122b-a10b| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | ¥0.80 | ¥6.40 |
| Prompts over 128K tokens | ¥2.00 | ¥16.00 |
Prices from 阿里云百炼：模型价格 (opens in a new tab) (checked Nov 2, 2026)
qwen3.5-122b-a10b| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard no longer listed since Oct 21, 2026 | $0.115 | $0.917 |
| Prompts over 128K tokens no longer listed since Oct 21, 2026 | $0.287 | $2.294 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 2, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Built-in tools
- Web search
- Licence
- apache-2.0
- Family
- qwen
- Model ID
Not stated on Alibaba Qwen’s pages: max input, reasoning efforts, max thinking budget, knowledge cutoff, aliases.
Run locally
Weights: Qwen/Qwen3.5-122B-A10B- Parameters 125.1B
- Active 10B · 256 experts, 8 per token
- Native precision BF16
- Layers 48
- KV cache per token 24 KB
- Native context 256K (model card)
- Config positions 256K (config.json max_position_embeddings)
- API context 256K (maker’s API)
- Needs
- ≈ 65.2 GB (weights 61.9 + KV cache 0.2 + overhead 3.1)
- Usable
- 21.6 GB (90% of its memory)
- In system memory
- 43.8 GB · 14/48 layers on the GPU (--n-gpu-layers 14)
- Generation speed
- 11–17 tok/s (reads the active 10B per token)
- First token
- about 0.32–0.48 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 233.0 GB | ≈ 244.8 | ✕Doesn’t fit | — |
| Q8_0 | 123.8 GB | ≈ 130.2 | ✕Doesn’t fit | — |
| FP8maker’s file | 118.4 GB | ≈ 124.5 | ✕Doesn’t fit | — |
| Q6_K | 95.7 GB | ≈ 100.6 | ✕Doesn’t fit | — |
| Q5_K_M | 82.9 GB | ≈ 87.2 | ✕Doesn’t fit | — |
| Q5_0 | 80.1 GB | ≈ 84.3 | ✕Doesn’t fit | — |
| Q4_K_M | 70.8 GB | ≈ 74.5 | ○Needs system memory 10–14 tok/s | — |
| Q4_0 | 65.5 GB | ≈ 69.0 | ○Needs system memory 11–16 tok/s | — |
| INT4 (AWQ / GPTQ)maker’s file | 73.4 GB | ≈ 77.3 | ○Needs system memory 9–13 tok/s | — |
| IQ4_XS | 61.9 GB | ≈ 65.2 | ○Needs system memory 11–17 tok/s | — |
| Q3_K_Mquality drops | 56.9 GB | ≈ 60.0 | ○Needs system memory 21–32 tok/s | — |
| IQ3_XXSquality drops | 44.6 GB | ≈ 47.0 | ○Needs system memory 27–41 tok/s | — |
| Q2_Kquality drops | 43.7 GB | ≈ 46.1 | ○Needs system memory 28–42 tok/s | — |
| IQ2_XXSquality drops | 30.0 GB | ≈ 31.7 | ○Needs system memory 42–63 tok/s | — |
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 NVIDIA RTX PRO 6000 Blackwell Workstation Edition; unified memory Apple M5 Max (40-core GPU) · 128 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 us- LMArena Text 1,417
#86 of 163 listed models · CI 1,412–1,421 · 29,712 votes
- Epoch AI · Mystery Game Puzzles 17%
#54 of 77 listed models · reasoning off · ±3.78
- EQ-Bench Longform Writing 54.3
#72 of 92 listed models
- LMArena Text · Chinese 1,458
#80 of 161 listed models · CI 1,444–1,471 · 2,123 votes
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 19 – 28, 2026
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 28, 2026
- 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 →- Context window 256K → 262.14K
- 2 new prices on SiliconFlow, China Input ¥0.80 · Output ¥6.40
- 1 price dropped on Alibaba Cloud Model Studio Output (Reasoning on) $0.917
- 2 prices dropped on Alibaba Cloud Model Studio, International Output (Reasoning off) $3.20 · Output (Reasoning on) $3.20
Sources
- Alibaba Cloud Model Studio pricing (opens in a new tab) alibabacloud.com · checked Nov 2, 2026
- 硅基流动：模型价格in Chinese (opens in a new tab) siliconflow.cn · checked Nov 1, 2026
- 阿里云百炼：模型价格in Chinese (opens in a new tab) help.aliyun.com · checked Nov 2, 2026
- 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 Nov 1, 2026
- Qwen3.5 122B-A10B model (opens in a new tab) alibabacloud.com · checked Oct 30, 2026
- Alibaba Cloud Model Studio: newly released models (opens in a new tab) alibabacloud.com · checked Nov 2, 2026
- Qwen/Qwen3.5-122B-A10B model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- models.dev: qwen3.5-122b-a10b (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
- qwen3.5-122b-a10b (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Nov 5, 2026
- Qwen/Qwen3.5-122B-A10B model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- Qwen/Qwen3.5-122B-A10B model card (opens in a new tab) huggingface.co · checked Oct 30, 2026
- Qwen/Qwen3.5-122B-A10B config.json (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3.5-122B-A10B files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- Qwen/Qwen3.5-122B-A10B-FP8 files (opens in a new tab) huggingface.co · checked Nov 1, 2026
- Qwen/Qwen3.5-122B-A10B-GPTQ-Int4 files (opens in a new tab) huggingface.co · checked Nov 1, 2026
- Qwen/Qwen3.5-122B-A10B README.md (opens in a new tab) huggingface.co · checked Nov 4, 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