Qwen3 30B A3B Thinking 2507 — Hardware Requirements & GPU Compatibility
ChatFunctions
Qwen3 30B A3B Thinking 2507 is the reasoning-focused variant of Alibaba's 30-billion-parameter mixture-of-experts model, updated in July 2025. Like its instruct sibling, it activates only about 3 billion parameters per token, keeping resource demands low while enabling multi-step reasoning and chain-of-thought problem solving. This thinking variant is designed for tasks that benefit from deliberate, step-by-step logic such as math, coding puzzles, and analytical questions. Its efficient MoE design means users with modest GPUs can still access strong reasoning capabilities without needing datacenter-class hardware.
Runs great on a 24 GB GPU
Runs from 12 GB (IQ2_M · 16K)Best on 24 GB (Q4_K_M · ~173 tok/s · 64K)Macs from 32 GB (~29 tok/s)
Score 100.6#45 of 92 open#9 of 34 that fit 24 GBApache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
100.6
- 90% range 97.0–104.2
- #45 of 92 open models
- #9 of 34 that fit 24 GB
Run Qwen3 30B A3B Thinking 2507
Best fit for your MacBook Pro 14" M3 Pro (36 GB). Every other method, OS and quant is in the step-by-step guide.
Recommended for your MacBook Pro 14" M3 Pro (36 GB)
mlx_lm.chat --model lmstudio-community/Qwen3-30B-A3B-Thinking-2507-MLX-4bitMLX repo with its own quantisation
Download: Qwen3-30B-A3B-Thinking-2507-Q4_K_M.gguf18.56 GBunsloth
Other ways
each opens step-by-stepRun in cloud
Fits on RTX A5000 (24 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~148 tok/s
- generation speed
- Cost per 1M output tokens
- $0.45
- per 1M output tokens
How Much VRAM Does Qwen3 30B A3B Thinking 2507 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On your device | |
|---|---|---|---|---|
| 13.4 GB | 14.9 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~42 tok/s | |
| 13.8 GB | 15.3 GB | 3-bit small — 3-bit small quantization | Fits: 256K context · ~42 tok/s | |
| 15.3 GB | 16.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~39 tok/s | |
| 15.7 GB | 17.2 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 256K context · ~39 tok/s | |
| 18.7 GB | 20.2 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~34 tok/s | |
| 22.1 GB | 23.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~31 tok/s | |
| 25.6 GB | 27.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~28 tok/s | |
| 30.9 GB | 32.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~24 tok/s |
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 MacBook Pro 14" M3 Pro (36 GB) · 13.1 GB free · ~34 tok/s
≥50 tok/s needs ≥182 GB/s · RTX 5090 ~227, RTX 3090 Ti ~173
Which Hardware Can Run Qwen3 30B A3B Thinking 2507?
Q4_K_M · 18.7 GBQwen3 30B A3B Thinking 2507 (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 262K context window can add up to 12.8 GB, bringing total usage to 31.5 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 125 devices with unified memory can run Qwen3 30B A3B Thinking 2507, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, 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 XTfits · 4.6 GB free · up to 64K ctx
6 GPUs · 2 Mac classes
RTX 3090 Ti~173Simulate output on RTX 3090 TiRTX 4090~173Simulate output on RTX 4090RTX 3090~166Simulate output on RTX 3090M4 Pro*24 GB~49Simulate output on Mac Mini M4 Pro (24 GB)M324 GB~26Simulate output on iMac 24" M3 (24 GB)48 GB
48 GB tier →fits · 28.6 GB free · up to 256K ctx
2 Mac classes · 1 device family
M3 Max48 GB~60Simulate output on MacBook Pro 14" M3 Max (48 GB)M4 Pro*48 GB~49Simulate output on Mac Mini M4 Pro (48 GB)Snapdragon X2 Elite Extreme (X2E-96-100)~54Simulate output on Snapdragon X2 Elite Extreme Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Qwen3 30B A3B Thinking 2507?
The llmrun Score merges 8 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 Thinking 2507
- Other models
- Best Score for its VRAM
#9 of 34 that fit 24 GBEvery model here fits your MacBook Pro 14" M3 Pro (36 GB) (36 GB)
Each dot is a model at the best quant that fits a 24 GB GPU. The line joins the models with the best Score for their 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 8 with a result for this model; badges show who ran the test.
- GPQA Diamond
Epoch AI · Jul 2025Independent
Independent70.1%
#32/97 open
- AIME 2024/2025
Epoch AI · Jul 2025Independent
Independent70.3%
#27/85 open
- MMLU-Pro
TIGER-LabIndependent
Independent80.9%
#22/144 open
- SciCode
Epoch AI · Jul 2025Lab-reported
Lab-reported33.3%
#48/65 open
- CritPt
Epoch AI · Jul 2025Lab-reported
Lab-reported0.3%
#41/65 open
- Chess Puzzles
Epoch AI · Jul 2025Independent
Independent8.0%
#26/67 open
In the 24 GB class
34 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
121.5
~38 tok/s · 17.9 GB
- #2
Qwen3.6 27BAlibaba
111.4
~38 tok/s · 17.9 GB
- #3
Qwen3.6 35B A3BAlibaba
106.9
~151 tok/s · 22.0 GB
- #4
Gemma 4 31B ITGoogle
106.1
~32 tok/s · 21.7 GB
- #5
Qwen3.5 35B A3BAlibaba
105.6
~151 tok/s · 22.0 GB
- #6
Gemma 4 26B A4B ITGoogle
105.4
~171 tok/s · 16.5 GB
Alternatives to Qwen3 30B A3B Thinking 2507
Qwen 3 family · 77 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
- 20.9 higher Score
- 1.6 GB less VRAM
- 135 tok/s slower
Score 121.5 · 17.9 GB · ~38 tok/s
Fits in less VRAM
GPT OSS 20B
OpenAI
- 4.4 lower Score
- 6.3 GB less VRAM
- 17 tok/s faster
Score 96.2 · 13.1 GB · ~190 tok/s
Other vendor
Gemma 4 31B IT
Google
- 5.5 higher Score
- 2.3 GB more VRAM
- 141 tok/s slower
Score 106.1 · 21.7 GB · ~32 tok/s
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.6 27BAlibaba | 111.4 | 17.9 GB | ~38 | similar score |
| Qwen3.6 35B A3BAlibaba | 106.9 | 22 GB | ~151 | similar score |
| Qwen3.5 35B A3BAlibaba | 105.6 | 22 GB | ~151 | similar score |
| Gemma 4 26B A4B ITGoogle | 105.4 | 16.5 GB | ~171 | 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 |
| DeepSeek R1 Distill Qwen 32BDeepSeek | 97.0 | 23 GB | ~34 | same size |
| QwQ 32BAlibaba | 96.1 | 23 GB | ~34 | same size |
| Magistral Small 2506Mistral AI | 88.7 | 17.8 GB | ~44 | same size |
Fine-tunes & variants(2)
Specifications
- Publisher
- Alibaba
- Family
- Qwen 3
- Parameters
- 30.5B
- Active parameters
- 3.4B per token
- Architecture
- Qwen3MoeForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-07-29
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3 30B A3B Thinking 2507 need?
Qwen3 30B A3B Thinking 2507 requires 18.7 GB of VRAM at Q4_K_M, or 61.5 GB at BF16. Full 262K context adds up to 12.8 GB (31.5 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 ≈ 13.2 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Qwen3 30B A3B Thinking 2507?
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 Thinking 2507?
For Qwen3 30B A3B Thinking 2507, 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 Thinking 2507 on a Mac?
Yes, but only at lower quantizations. The smallest Mac that can run Qwen3 30B A3B Thinking 2507 is iPad Pro M5 13" (16 GB) at IQ2_XXS; 136 of the 156 Macs we list can run it at some quantization. For Q4_K_M (18.7 GB) you need a Mac with more unified memory.
Can I run Qwen3 30B A3B Thinking 2507 locally?
Yes — Qwen3 30B A3B Thinking 2507 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3 30B A3B Thinking 2507?
At Q4_K_M, Qwen3 30B A3B Thinking 2507 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 Thinking 2507?
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 Thinking 2507?
8 consumer GPUs can run Qwen3 30B A3B Thinking 2507 at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
Which devices can run Qwen3 30B A3B Thinking 2507?
125 devices with unified memory can run Qwen3 30B A3B Thinking 2507 at Q4_K_M (18.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.