Qwen3.5 122B A10B — Hardware Requirements & GPU Compatibility
Vision
Qwen3.5 122B A10B is Alibaba's 125-billion-parameter mixture-of-experts model from the Qwen 3.5 medium series, with about 10 billion parameters active per token (the A10B in its name). Because only the active experts run per token, inference is markedly faster than a dense model of comparable size, though all the weights still need to be held in memory. It is a unified vision-language model, handling images alongside text for reasoning, coding, and agentic workflows. Given its size, local inference needs a multi-GPU workstation or a large unified-memory machine; most people access a model this size through a hosted endpoint instead. It supports a 262K token context window and is released under the Apache 2.0 license, allowing unrestricted commercial and research use. Published in February 2026, it sits alongside Qwen3.5-Flash, Qwen3.5-27B, and Qwen3.5-35B-A3B in Alibaba's medium-model series.
331.9K downloads
622 likesSpecifications
- Publisher
- Alibaba
- Family
- Qwen 3.5
- Parameters
- 125.1B
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-02-24
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Qwen3.5 122B A10B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 250.6 GB | 260.1 GB | 250.17 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Qwen3.5 122B A10B?
BF16 · 250.6 GBQwen3.5 122B A10B (BF16) requires 250.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 326+ GB is recommended. Using the full 262K context window can add up to 9.6 GB, bringing total usage to 260.1 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Qwen3.5 122B A10B?
BF16 · 250.6 GB3 devices with unified memory can run Qwen3.5 122B A10B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download Qwen3.5 122B A10B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Qwen3.5 122B A10B need?
Qwen3.5 122B A10B requires 250.6 GB of VRAM at BF16. Full 262K context adds up to 9.6 GB (260.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 125.1B × 16 bits ÷ 8 = 250.2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 9.9 GB (at full 262K context)
VRAM usage by quantization
BF16250.6 GBBF16 + full context260.1 GB- Can NVIDIA GeForce RTX 5090 run Qwen3.5 122B A10B?
No — Qwen3.5 122B A10B requires at least 250.6 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Qwen3.5 122B A10B on a Mac?
Qwen3.5 122B A10B requires at least 250.6 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Qwen3.5 122B A10B locally?
Yes — Qwen3.5 122B A10B can run locally on consumer hardware. At BF16 quantization it needs 250.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen3.5 122B A10B?
At BF16, Qwen3.5 122B A10B can reach ~67 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B300 → 8000 ÷ 250.6 × 0.65 = ~133 tok/s
Estimated speed at BF16 (250.6 GB)
~133 tok/s~67 tok/s~67 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwen3.5 122B A10B?
At BF16, the download is about 250.17 GB.
- Which GPUs can run Qwen3.5 122B A10B?
No single consumer GPU has enough VRAM to run Qwen3.5 122B A10B at BF16 (250.6 GB). Multi-GPU or professional hardware is required.
- Which devices can run Qwen3.5 122B A10B?
4 devices with unified memory can run Qwen3.5 122B A10B at BF16 (250.6 GB), including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.