Qwen3 Next 80B A3B Instruct — Hardware Requirements & GPU Compatibility
Chat
Qwen3 Next 80B A3B Instruct is a Mixture of Experts (MoE) model from Alibaba Cloud's Qwen 3 series, with approximately 81.3 billion total parameters and around 3 billion active parameters per forward pass. This extreme ratio between total and active parameters allows the model to encode extensive knowledge across its expert layers while maintaining very fast per-token inference, making it an unusually efficient design for its capability level. The model is instruction-tuned for general-purpose chat and requires VRAM proportional to its full 80B parameter count for weight loading, typically needing high-VRAM GPUs or quantized multi-GPU setups. Its low active parameter count results in fast generation speeds despite the large total model size. Released under the Apache 2.0 license.
323.6K downloads
1.0K likesSpecifications
- Publisher
- Alibaba
- Family
- Qwen 3
- Parameters
- 81.3B
- Architecture
- Qwen3NextForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-09-09
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Qwen3 Next 80B A3B Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 35.0 GB | 47.8 GB | 34.56 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 36.0 GB | 48.8 GB | 35.58 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 40.0 GB | 52.8 GB | 39.65 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 41.1 GB | 53.9 GB | 40.66 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 49.2 GB | 62.0 GB | 48.79 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 58.3 GB | 71.1 GB | 57.94 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 67.5 GB | 80.3 GB | 67.09 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 81.7 GB | 94.5 GB | 81.32 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Qwen3 Next 80B A3B Instruct?
Q4_K_M · 49.2 GBQwen3 Next 80B A3B Instruct (Q4_K_M) requires 49.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 64+ GB is recommended. Using the full 262K context window can add up to 12.8 GB, bringing total usage to 62.0 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Qwen3 Next 80B A3B Instruct?
Q4_K_M · 49.2 GB22 devices with unified memory can run Qwen3 Next 80B A3B Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 96GB).
Runs great
— Plenty of headroom
Where to Download Qwen3 Next 80B A3B Instruct
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 Next 80B A3B Instruct need?
Qwen3 Next 80B A3B Instruct requires 49.2 GB of VRAM at Q4_K_M, or 163.1 GB at BF16. Full 262K context adds up to 12.8 GB (62.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 81.3B × 4.8 bits ÷ 8 = 48.8 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 13.2 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M49.2 GBQ4_K_M + full context62.0 GB- Can NVIDIA GeForce RTX 4090 run Qwen3 Next 80B A3B Instruct?
Yes, at IQ2_XXS (22.8 GB) or lower. Higher quantizations like IQ2_XS (24.8 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Qwen3 Next 80B A3B Instruct?
For Qwen3 Next 80B A3B Instruct, Q4_K_M (49.2 GB) offers the best balance of quality and VRAM usage. Q4_K_L (50.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 22.8 GB.
VRAM requirement by quantization
IQ2_XXS22.8 GBQ2_K35.0 GBIQ4_XS44.1 GBQ4_K_M ★49.2 GBQ5_051.2 GBBF16163.1 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwen3 Next 80B A3B Instruct on a Mac?
Qwen3 Next 80B A3B Instruct requires at least 22.8 GB at IQ2_XXS, 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 Next 80B A3B Instruct locally?
Yes — Qwen3 Next 80B A3B Instruct can run locally on consumer hardware. At Q4_K_M quantization it needs 49.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen3 Next 80B A3B Instruct?
At Q4_K_M, Qwen3 Next 80B A3B Instruct can reach ~89 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 B200 → 8000 ÷ 49.2 × 0.65 = ~106 tok/s
Estimated speed at Q4_K_M (49.2 GB)
~106 tok/s~106 tok/s~89 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwen3 Next 80B A3B Instruct?
At Q4_K_M, the download is about 48.79 GB. The full-precision BF16 version is 162.65 GB. The smallest option (IQ2_XXS) is 22.36 GB.
- Which GPUs can run Qwen3 Next 80B A3B Instruct?
No single consumer GPU has enough VRAM to run Qwen3 Next 80B A3B Instruct at Q4_K_M (49.2 GB). Multi-GPU or professional hardware is required.
- Which devices can run Qwen3 Next 80B A3B Instruct?
23 devices with unified memory can run Qwen3 Next 80B A3B Instruct at Q4_K_M (49.2 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.