QwenQwen3.5-122B-A10B on NVIDIA GeForce RTX 4090
RTX 4090 cannot run Qwen3.5-122B-A10B. 24 GB VRAM is insufficient at any quantization level.
Model Size
122B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantization
Q3_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for Qwen3.5-122B-A10B on NVIDIA GeForce RTX 4090 at Q3_K_M. This pairing has limitations — check the rating and notes below.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q3_K_M | 19 tok/s | 632ms | ✗ Offload | Marginal | estimated |
Notes
Q3_K_M
Q3_K_M needs 28GB but only 24GB available. MoE: only 10B params active per token — faster than total size suggests. Offloading still limits throughput.
About Qwen3.5-122B-A10B
Qwen3.5-122B-A10B (122B) is a chat, coding, ai coding, reasoning, multi-purpose model. 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.
View all Qwen3.5-122B-A10B hardware options →About NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 has 24 GB at 1008 GB/s. Street price: $1,799.
See all models NVIDIA GeForce RTX 4090 can run →Builds with NVIDIA GeForce RTX 4090
Estimate method: Estimated from Qwen 3 32B and MoE benchmarks with size/architecture scaling. Reference hardware source: github.com (2026-03-24)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.