Leaderboard / Alibaba (Qwen)

Qwen3-Coder 30B-A3B

Name: Qwen3-Coder 30B-A3B
Price: 0.262 USD
Author: Alibaba (Qwen)

Alibaba (Qwen) · Qwen3-Coder · released 2025-07-31 · data checked 2026-11-01 Needs verification

Qwen3-Coder 30B-A3B is a 30.5B-parameter Mixture-of-Experts model (3.3B active per token) from Alibaba (Qwen) (China), released 2025-07-31 under the Apache-2.0 license. It doesn't have enough reported benchmarks for an index score yet. It needs about 20.4 GB of memory at 4-bit with an 8K-token context and costs $0.26 per million tokens through the cheapest API provider.

Small LM Index

—

Needs 2 core benchmarks (has 1)

Parameters

30.5B

3.3B active · MoE

Price per 1M tokens

$0.26

$0.15 in / $0.60 out · blended 3:1

Context window

262K

tokens

Benchmarks

Each bar shows this model's score. The tick marks the best medium model on that benchmark. Sources: 1 reported by Alibaba (Qwen). How we label sources.

SWE-bench Verified Lab-reported Coding51.6

Class best: Qwen3.6 27B 77.2

Specifications

Lab: Alibaba (Qwen) (CN · China)
Architecture: Mixture-of-Experts
Total parameters: 30.5B
Active parameters: 3.3B
Size class: Medium
Context window: 262K tokens
Input modalities: text
Reasoning: Instruct (no thinking)
License: Apache-2.0
Openness: Open weights
Memory to run: ~20.4 GB at 4-bit, 8K context (more sizes)
Hugging Face: 1.2M downloads (30 days) · 1.3K likes
API providers: 1 on OpenRouter
API price: $0.15 in / $0.60 out per 1M (OpenRouter, 2026-11-03)

Weights on Hugging Face ↗Try on OpenRouter ↗

Compare with

Qwen3-Coder 30B-A3B vs Qwen3 30B-A3B Thinking 2507 (30.5B, index 59.3)
Qwen3-Coder 30B-A3B vs Gemma 4 31B (30.7B, index 70.1)
Qwen3-Coder 30B-A3B vs Kanana-2 30B-A3B Thinking (30.7B, index 50.7)

Sources

https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct

Something wrong here? Report it.

Run it locally

Uses ggml-org/Qwen3-Coder-30B-A3B-Instruct-GGUF (Q4_K_M). Swap the tag for another size: BF16, Q4_K_M, Q8_0.

Ollama

ollama run hf.co/ggml-org/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_M

llama.cpp

llama-server -hf ggml-org/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_M

Then open http://localhost:8080 for a chat window.

MLX (Mac)

pip install -U mlx-lm
mlx_lm.chat --model mlx-community/Qwen3-Coder-30B-A3B-Instruct-4bit

vLLM (GPU server)

vllm serve Qwen/Qwen3-Coder-30B-A3B-Instruct

Full-precision weights, for a server GPU.

Open in LM Studio

Memory needed: weights, context cache and runtime buffers.

Quantization	4K context	32K context	256K context
16-bit F16	63 GB	65 GB	88 GB
8-bit Q8_0	34 GB	37 GB	59 GB
4-bit Q4_K_M	20 GB	23 GB	45 GB

Check it against your GPU, Mac or phone →