Qwen3.5 122B A10B Abliterated — Hardware Requirements & GPU Compatibility
Chat
Qwen3.5 122B A10B Abliterated is a 122.1B-parameter open language model from wangzhang in the Qwen 3.5 family. At BF16 it needs about 268.65 GB of VRAM — see which GPUs and Macs can run it below.
43 downloads
8 likesSpecifications
- Publisher
- wangzhang
- Family
- Qwen 3.5
- Parameters
- 122.1B
- Release Date
- 2026-03-02
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Qwen3.5 122B A10B Abliterated Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 268.6 GB | — | 244.22 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 Abliterated?
BF16 · 268.6 GBQwen3.5 122B A10B Abliterated (BF16) requires 268.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 350+ GB is recommended. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Qwen3.5 122B A10B Abliterated?
BF16 · 268.6 GB2 devices with unified memory can run Qwen3.5 122B A10B Abliterated, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Qwen3.5 122B A10B Abliterated need?
Qwen3.5 122B A10B Abliterated requires 268.6 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 122.1B × 16 bits ÷ 8 = 244.2 GB
KV Cache + Overhead ≈ 24.4 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF16268.6 GB- Can NVIDIA GeForce RTX 5090 run Qwen3.5 122B A10B Abliterated?
No — Qwen3.5 122B A10B Abliterated requires at least 268.6 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Qwen3.5 122B A10B Abliterated on a Mac?
Qwen3.5 122B A10B Abliterated requires at least 268.6 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 Abliterated locally?
Yes — Qwen3.5 122B A10B Abliterated can run locally on consumer hardware. At BF16 quantization it needs 268.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of Qwen3.5 122B A10B Abliterated?
At BF16, the download is about 244.22 GB.
- Which GPUs can run Qwen3.5 122B A10B Abliterated?
No single consumer GPU has enough VRAM to run Qwen3.5 122B A10B Abliterated at BF16 (268.6 GB). Multi-GPU or professional hardware is required.
- Which devices can run Qwen3.5 122B A10B Abliterated?
2 devices with unified memory can run Qwen3.5 122B A10B Abliterated at BF16 (268.6 GB), including 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.