Qwen3 30B A3B.w8a8 — Hardware Requirements & GPU Compatibility
ChatFunctions
Qwen3 30B A3B.w8a8 is a 30.6B-parameter open language model from nytopop in the Qwen 3 family. It supports a context window of up to 40,960 tokens. At Q4_K_M it needs about 18.73 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 16 GB (Q3_K_M · 16K)Best on 24 GB (Q4_K_M · ~173 tok/s · 40K)Macs from 18 GB (Q2_K · ~42 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen3 30B A3B.w8a8
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve nytopop/Qwen3-30B-A3B.w8a8 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX A5000 (24 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~147 tok/s
- generation speed
- Cost per 1M output tokens
- $0.30
- per 1M output tokens
How Much VRAM Does Qwen3 30B A3B.w8a8 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 13.4 GB | 14.9 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 40K context · ~204 tok/s | |
| 15.3 GB | 16.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 40K context · ~192 tok/s | |
| 18.7 GB | 20.2 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 40K context · ~173 tok/s | |
| 22.2 GB | 23.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~157 tok/s | |
| 25.6 GB | 27.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 26.3 GB | |
| 31.0 GB | 32.5 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 31.7 GB | |
| 61.5 GB | 63 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 62.2 GB |
Selected Q4_K_M
4-bit medium quantization19.4GBat 16K context
- Weights
- 18.3 GB
- KV cache
- 0.8 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 4.6 GB free · ~173 tok/s
≥50 tok/s needs ≥183 GB/s · RTX 5090 ~226, RTX 3090 Ti ~173
Which Hardware Can Run Qwen3 30B A3B.w8a8?
Q4_K_M · 18.7 GBQwen3 30B A3B.w8a8 (Q4_K_M) requires 18.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 25+ GB is recommended. Using the full 41K context window can add up to 1.9 GB, bringing total usage to 20.6 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Qwen3 30B A3B.w8a8, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 0.6 GB free · up to 16K ctx
1 GPU
RX 7900 XT~72Simulate output on RX 7900 XT32–40 GB
fits · 12.6 GB free · up to 40K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~226Simulate output on RTX 5090M5 Max36 GB~62Simulate output on Mac Studio M5 Max (36 GB)M532 GB~35Simulate output on MacBook Air 13" M5 (32 GB)Orin~55Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~35Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Qwen3 30B A3B.w8a8
Qwen 3 family · 79 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Hy Memory 30B A3BTencent | — | 19.1 GB | ~184 | same size |
| Granite Switch 4.1 30BIBM | — | 22.7 GB | ~35 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Muse Glimmer 30BMeta | — | 19.6 GB | ~36 | same size |
| NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA | — | 19.3 GB | ~197 | same size |
| Hy MT2 30B A3BTencent | — | 19.1 GB | ~170 | same size |
Specifications
- Publisher
- nytopop
- Family
- Qwen 3
- Parameters
- 30.6B
- Active parameters
- 3.4B per token
- Architecture
- Qwen3MoeForCausalLM
- Context Length
- 40,960 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-04-30
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3 30B A3B.w8a8 need?
Qwen3 30B A3B.w8a8 requires 18.7 GB of VRAM at Q4_K_M, or 61.5 GB at BF16. Full 41K context adds up to 1.9 GB (20.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 30.6B × 4.8 bits ÷ 8 = 18.3 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 2.3 GB (at full 41K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Qwen3 30B A3B.w8a8?
Yes, at Q5_K_M (22.2 GB) or lower. Higher quantizations like Q6_K (25.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Qwen3 30B A3B.w8a8?
For Qwen3 30B A3B.w8a8, Q4_K_M (18.7 GB) offers the best balance of quality and VRAM usage. Q5_K_M (22.2 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 13.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3 30B A3B.w8a8 on a Mac?
Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run Qwen3 30B A3B.w8a8, the smallest at Q2_K. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 18.7 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Qwen3 30B A3B.w8a8 locally?
Yes — Qwen3 30B A3B.w8a8 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3 30B A3B.w8a8?
At Q4_K_M, Qwen3 30B A3B.w8a8 can reach ~100 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~173 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 2.1 GB active ÷ (8000 × 0.65) = 0.40 ms, plus 48 layers × 0.055 ms = 2.64 ms, so 1000 ÷ 3.04 ms = ~329 tok/s
Estimated speed at Q4_K_M (18.7 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen3 30B A3B.w8a8?
At Q4_K_M, the download is about 18.33 GB. The full-precision BF16 version is 61.11 GB. The smallest option (Q2_K) is 12.99 GB.
Which GPUs can run Qwen3 30B A3B.w8a8?
8 consumer GPUs can run Qwen3 30B A3B.w8a8 at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Qwen3 30B A3B.w8a8?
122 devices with unified memory can run Qwen3 30B A3B.w8a8 at Q4_K_M (18.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, 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.