What GPU do I need to run Qwen/Qwen3.5-122B-A10B?
A 125B (MoE) language model for chat and instruction-following. 125.1B parameters, published in BF16. View on Hugging Face
Qwen3.5-122B-A10B is published by Qwen on Hugging Face, with 863,674 downloads and 612 likes to date. It's a Qwen3_5MoeForConditionalGeneration model built for image-text-to-text, published natively in BF16.
What Qwen3.5-122B-A10B is
Qwen3.5-122B-A10B is a 125B-parameter mixture-of-experts language model published by Alibaba (Qwen) on Hugging Face. It is released under Apache 2.0.
License note: fully permissive, no gating and no usage restrictions. Facts in this section are sourced from Qwen3.5-122B-A10B's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Chat assistants
- Instruction following
- Synthetic data generation
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 233.0 GB | 279.6 GB | RTX A6000 | 6 | $2.18/hr |
| FP8 (quantized) | 116.5 GB | 139.8 GB | AMD MI300X | 1 | $2.63/hr |
| cheaper alt. | RTX 4000 SFF Ada | 7 | $1.39/hr | ||
| INT4 (quantized) | 58.2 GB | 69.9 GB | A100 | 1 | $1.16/hr |
| cheaper alt. | RTX A5000 | 3 | $0.528/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Qwen3.5-122B-A10B at its published (BF16) precision: 6× RTX A6000, at $0.363/hr per GPU ($2.18/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Qwen3.5-122B-A10B: KV cache by context length
The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.
Hybrid: only the full-attention layers cache per token; the other layers keep a fixed-size state. Cached per token: 24,576 bytes at 16-bit.
| Context | KV cache, one sequence |
|---|---|
| 4K | 0.09 GB |
| 32K | 0.75 GB |
| 128K | 3.0 GB |
| 256K (model maximum) | 6.0 GB |
Computed from the layer, head and window counts in the model's own configuration (Qwen/Qwen3.5-122B-A10B), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.
Qwen3.5-122B-A10B: common questions
Can Qwen3.5-122B-A10B run on a single GPU?
No. At BF16 it needs 279.6 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 48.0 GB RTX A6000, and it takes 6 of them.
How many GPUs do I need to run Qwen3.5-122B-A10B?
6 at BF16. It needs 279.6 GB of VRAM and the cheapest capable live offer is a 48.0 GB RTX A6000, so 6 of them come to $2.18/hr in total.
Does quantizing Qwen3.5-122B-A10B lower the GPU bill?
Yes. At BF16 the cheapest live fit is 6 RTX A6000 cards at $2.18/hr. At INT4 (quantized) it drops to one A100 at $1.16/hr, provided a quantized checkpoint exists for it.
How to run Qwen3.5-122B-A10B
Run Qwen3.5-122B-A10B with vLLM
Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.
vllm serve Qwen/Qwen3.5-122B-A10B --tensor-parallel-size 6Run Qwen3.5-122B-A10B with Ollama
Verified against Ollama's own library listing.
ollama run qwen3.5:122bRun Qwen3.5-122B-A10B with GGUF quantizations
Prebuilt GGUF weights published at unsloth/Qwen3.5-122B-A10B-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUFSource: https://huggingface.co/unsloth/Qwen3.5-122B-A10B-GGUF
Deploy Qwen3.5-122B-A10B on Aquanode
Aquanode has no one-click deploy template for Qwen3.5-122B-A10B; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (6× RTX A6000 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU podWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Qwen3.5 models
- Qwen3.5-122B-A10B-FP8 (125.1B, F8_E4M3)
- Qwen3.5-397B-A17B (403.4B, BF16)
- Qwen3.5-397B-A17B-FP8 (403.4B, F8_E4M3)
- Qwen3.5-35B-A3B-FP8 (36.0B, F8_E4M3)
- Qwen3.5-35B-A3B (36.0B, BF16)
Lineage
Quantized and fine-tuned versions
Alternatives at this size
Other models for image-text-to-text within about a third of Qwen3.5-122B-A10B's 125.1B parameters, from other model lines.
- Llama-4-Scout-17B-16E-Instruct (108.6B, BF16)
- GLM-4.5V (107.7B, BF16)
- Darwin-180B-RSI (180.0B, BF16)
More on Qwen3.5-122B-A10B
Fits on a 288 GB GPU at BF16: every model that fits in 288 GB.
Fits on a 141 GB GPU at FP8: every model that fits in 141 GB.
Fits on an 80 GB GPU at INT4: every model that fits in 80 GB.
Best vision-language models: how Qwen3.5-122B-A10B ranks against the rest.
Related reading: RTX A6000 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.
