Qwen3-30B-A3B-Instruct-2507-bf16

mlx-community/Qwen3-30B-A3B-Instruct-2507-bf16

Text generation · mlx

bf16 Open on Hugging Face

Parameters

31B

Weights (est.)

≈ 61.1 GB

Mac memory (est.)

96 GB+

Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.

Run it

With mlx-lm on an Apple silicon Mac:

pip install mlx-lmmlx_lm.generate --model mlx-community/Qwen3-30B-A3B-Instruct-2507-bf16 --prompt "Hello"

Details

Base model: Qwen/Qwen3-30B-A3B-Instruct-2507 (finetune)
Vendor: Qwen
Task: Text generation
Quantisation: bf16
Licence: apache-2.0
Downloads: 39 in the last 30 days · 2.2K all time · 0 likes
Published: 2025-08-01 · updated 2025-08-01 (1y ago)
Tags: qwen3_moe

Other MLX builds of Qwen/Qwen3-30B-A3B-Instruct-2507

Build	Quantisation	Weights	Mac memory	Downloads
Qwen3-30B-A3B-Instruct-2507-4bit	4-bit	≈ 17.2 GB	24 GB+	6.6K
Qwen3-30B-A3B-Instruct-2507-5bit	5-bit	≈ 21.0 GB	32 GB+	67
Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr9e-8	5-bit DWQ	≈ 21.0 GB	32 GB+	46
Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr5e-7	5-bit DWQ	≈ 21.0 GB	32 GB+	35
Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr3e-8	5-bit DWQ	≈ 21.0 GB	32 GB+	30
Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr2e-7	5-bit DWQ	≈ 21.0 GB	32 GB+	30
Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr1e-7	5-bit DWQ	≈ 21.0 GB	32 GB+	27
Qwen3-30B-A3B-Instruct-2507-6bit	6-bit	≈ 24.8 GB	32 GB+	69
Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr1e-8	6-bit DWQ	≈ 24.8 GB	32 GB+	58
Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr5e-8	6-bit DWQ	≈ 24.8 GB	32 GB+	31
Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr3e-7	6-bit DWQ	≈ 24.8 GB	32 GB+	28
Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr8e-8	6-bit DWQ	≈ 24.8 GB	32 GB+	27
Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr8e-7	6-bit DWQ	≈ 24.8 GB	32 GB+	27
Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr5e-9	6-bit DWQ	≈ 24.8 GB	32 GB+	25
Qwen3-30B-A3B-Instruct-2507-8bit	8-bit	≈ 32.4 GB	48 GB+	216
Qwen3-30B-A3B-Instruct-2507-bf16 (this one)	bf16	≈ 61.1 GB	96 GB+	39