Qwen3 30B A3B — Hardware Requirements & GPU Compatibility
ChatFunctions
Qwen3 30B A3B is a Mixture of Experts (MoE) model from Alibaba Cloud's Qwen 3 series, with 30 billion total parameters and approximately 3 billion active parameters per forward pass. The MoE architecture delivers quality significantly above what a standard 3B dense model could achieve, while keeping per-token compute costs low. It supports hybrid thinking mode for flexible reasoning. The model requires VRAM proportional to its full 30B parameter count for weight loading, but its low active parameter count results in fast inference throughput. It is an efficient option for users who want quality beyond dense small models without the full cost of larger architectures. Released under the Apache 2.0 license.
Runs great on a 24 GB GPU
Runs from 12 GB (IQ2_M · 16K)Best on 24 GB (Q4_K_M · ~173 tok/s · 40K)Macs from 16 GB (IQ2_M · ~56 tok/s)
Score 93.9#74 of 106 open#18 of 36 that fit 24 GBApache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
93.9
- 90% range 90.6–97.2
- #74 of 106 open models
- #18 of 36 that fit 24 GB
Run Qwen3 30B A3B
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
ollama run hf.co/Qwen/Qwen3-30B-A3B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 4.6 GB free · 16K context
Download: Qwen3-30B-A3B-Q4_K_M.gguf18.56 GBQwen
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3090 (24 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~166 tok/s
- generation speed
- Cost per 1M output tokens
- $0.32
- per 1M output tokens
How Much VRAM Does Qwen3 30B A3B 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 · ~205 tok/s | |
| 13.8 GB | 15.3 GB | 3-bit small — 3-bit small quantization | Fits: 40K context · ~202 tok/s | |
| 15.3 GB | 16.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 40K context · ~192 tok/s | |
| 15.7 GB | 17.2 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 40K context · ~190 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 | |
| 22.1 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 | |
| 30.9 GB | 32.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 31.6 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 ≥182 GB/s · RTX 5090 ~227, RTX 3090 Ti ~173
Which Hardware Can Run Qwen3 30B A3B?
Q4_K_M · 18.7 GBQwen3 30B A3B (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, 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 5090~227Simulate output on RTX 5090M5 Max36 GB~63Simulate 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
How good is Qwen3 30B A3B?
The llmrun Score merges 6 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the 24 GB tier
- Qwen3 30B A3B
- Other models
- Best Score for its VRAM
#18 of 36 that fit 24 GB
Each dot is a model at the best quant that fits a 24 GB GPU. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.
Full 24 GB ranking →Benchmarks
The 6 boards that weigh most in the llmrun Score, of 7 with a result for this model; badges show who ran the test.
- GPQA Diamond
Epoch AI · Apr 2025Independent
Independent61.7%
#43/100 open
- LMArena Text
LMArena · Oct 2026Arena
Arena1326.7
#91/188 open
- AIME 2024/2025
Epoch AI · Apr 2025Independent
Independent62.8%
#37/88 open
- WeirdML
Epoch AI · Apr 2025Independent
Independent29.8%
#39/47 open
- DTBench
Epoch AI · Apr 2025Lab-reported
Lab-reported60.3%
#49/70 open
- LMCA
Epoch AI · Apr 2025Lab-reported
Lab-reported15.8%
#42/56 open
In the 24 GB class
36 models fit 24 GBSame Score, only models that fit 24 GB at their best quant: the ranking a 24 GB owner actually chooses from.
- #1
Qwen3.8 27BAlibaba
122.0
~38 tok/s · 17.9 GB
- #2
Qwen3.6 27BAlibaba
111.2
~38 tok/s · 17.9 GB
- #3
Qwen3.6 35B A3BAlibaba
106.8
~151 tok/s · 22.0 GB
- #4
Gemma 4 31B ITGoogle
106.7
~32 tok/s · 21.7 GB
- #5
Gemma 4 26B A4B ITGoogle
105.8
~171 tok/s · 16.5 GB
- #6
Qwen3.5 35B A3BAlibaba
105.8
~151 tok/s · 22.0 GB
Alternatives to Qwen3 30B A3B
Qwen 3 family · 79 models →Official models with an llmrun Score, each answering one question; numbers are at the best quant that fits a 24 GB GPU.
Best alternative at this size
Qwen3.8 27B
Alibaba
- 28.1 higher Score
- 1.6 GB less VRAM
- 135 tok/s slower
Score 122.0 · 17.9 GB · ~38 tok/s
Fits in less VRAM
GPT OSS 20B
OpenAI
- 2.5 higher Score
- 6.3 GB less VRAM
- 17 tok/s faster
Score 96.4 · 13.1 GB · ~190 tok/s
Other vendor
Gemma 4 31B IT
Google
- 12.8 higher Score
- 2.3 GB more VRAM
- 141 tok/s slower
Score 106.7 · 21.7 GB · ~32 tok/s
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | similar score |
| Qwen3.6 35B A3BAlibaba | 106.8 | 22 GB | ~151 | similar score |
| Gemma 4 26B A4B ITGoogle | 105.8 | 16.5 GB | ~171 | similar score |
| Qwen3.5 35B A3BAlibaba | 105.8 | 22 GB | ~151 | similar score |
| Qwen3.5 27BAlibaba | 103.8 | 17.9 GB | ~38 | similar score |
| Seed OSS 36B InstructByteDance-Seed | 102.5 | 22.8 GB | ~31 | similar score |
| Qwen3.5 9BAlibaba | 99.4 | 6.6 GB | ~103 | similar score |
| Qwen3.5 4BAlibaba | 98.5 | 3.4 GB | ~201 | similar score |
| Phi 4Microsoft | 83.9 | 12.5 GB | ~69 | similar score |
| DeepSeek R1 Distill Qwen 32BDeepSeek | 97.2 | 23 GB | ~34 | same size |
Fine-tunes & variants(3)
Specifications
- Publisher
- Alibaba
- Family
- Qwen 3
- Parameters
- 30.5B
- Active parameters
- 3.4B per token
- Architecture
- Qwen3MoeForCausalLM
- Context Length
- 40,960 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-04-27
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3 30B A3B need?
Qwen3 30B A3B 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 = 30.5B × 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?
Yes, at Q5_K_L (22.5 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?
For Qwen3 30B A3B, Q4_K_M (18.7 GB) offers the best balance of quality and VRAM usage. Q4_K_L (19.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 8.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3 30B A3B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Qwen3 30B A3B, the smallest at IQ2_M. 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 locally?
Yes — Qwen3 30B A3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3 30B A3B?
At Q4_K_M, Qwen3 30B A3B 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) = 0.39535 ms, plus 48 layers × 0.055 ms = 2.64000 ms, so 1000 ÷ 3.03535 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?
At Q4_K_M, the download is about 18.32 GB. The full-precision BF16 version is 61.06 GB. The smallest option (IQ2_XXS) is 8.40 GB.
Which GPUs can run Qwen3 30B A3B?
8 consumer GPUs can run Qwen3 30B A3B 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?
122 devices with unified memory can run Qwen3 30B A3B 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.