Qwen3.5-122B-A10B
Qwen · Apache 2.0
Mixture of Experts: 122B total parameters, 10B active per token.
Mixture-of-Experts with 122B total parameters but only 10B active per token. Runs on far less VRAM than the total size suggests. Qwen's best open-weight MoE in the medium tier; excels at knowledge-heavy and vision tasks. Native multimodal. Apache 2.0 licensed.
- Parameters
- 122B
- Architecture
- MoE (10B active)
- Context
- 262,144 tokens
- Released
- 2026-02-24
- Engines
- llama.cpp, ollama, vLLM
- Builder Tools
- Continue, LM Studio, Open WebUI
Parameters
122B
VRAM
42 GB
Context
256K
Formats
4
GPUs
38
Qwen3.5-122B-A10B (122B) requires 42 GB VRAM at recommended quality (Q5_K_M). On NVIDIA Grace Blackwell Ultra GB300, expect approximately 200 tok/s at Q8_0. For the best experience, High-End Home AI Server ($3,842) is recommended.
Source: OwnRig methodology
42 GB
Q5_K_M
39 GB
256K tokens
Chat
VRAM Requirements
| Quality | Quantization | VRAM | File Size |
|---|---|---|---|
| full | Q8_0 | 65 GB | 61 GB |
| recommended | Q5_K_M | 42 GB | 39 GB |
| efficient | Q4_K_M | 35 GB | 33 GB |
| compressed | Q3_K_M | 28 GB | 26 GB |
Context Length Impact
KV cache VRAM at Q5_K_M quality. Longer context = more memory.
| Context | KV Cache | Total VRAM |
|---|---|---|
| 2K | 205 MB | 42.2 GBexceeds 24 GB |
| 4K | 307 MB | 42.3 GBexceeds 24 GB |
| 8K | 614 MB | 42.6 GBexceeds 24 GB |
| 16K | 1.3 GB | 43.3 GBexceeds 24 GB |
| 32K | 2.6 GB | 44.6 GBexceeds 24 GB |
| 64K | 5.1 GB | 47.1 GBexceeds 24 GB |
| 128K | 10.2 GB | 52.2 GBexceeds 24 GB |
Compatible GPUs
38 devicesShowing 38 of 38 entries
Builder Context
Qwen3.5-122B-A10B is commonly used with Continue, LM Studio, Open WebUI. For an AI coding workflow, pair it with an embedding model like nomic-embed-text for local RAG.
Frequently Asked Questions
- How much VRAM does Qwen3.5-122B-A10B need?
- Qwen3.5-122B-A10B requires 42 GB VRAM at recommended quality (Q5_K_M). At lower quality settings, it can fit in as little as 28 GB.
- What is the best GPU for Qwen3.5-122B-A10B?
- The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for Qwen3.5-122B-A10B, achieving 200 tok/s at Q8_0 with an excellent rating.
- Can I run Qwen3.5-122B-A10B on an RTX 4060 Ti?
- Qwen3.5-122B-A10B at Q3_K_M requires 42 GB VRAM, which exceeds the RTX 4060 Ti's 16 GB. Consider a lower quantization or a GPU with more VRAM.
- What quantization should I use for Qwen3.5-122B-A10B?
- For the best quality, use Q5_K_M (42 GB VRAM). If your GPU has limited VRAM, Q3_K_M (28 GB) is the most efficient option with acceptable quality.
- Is Qwen3.5-122B-A10B good for coding?
- Yes. Qwen3.5-122B-A10B is used with Continue, LM Studio, Open WebUI for local AI coding. For the best coding experience, pair it with an embedding model for local RAG.
Data confidence: estimated. Source
VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.Qwen is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.