geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
alibaba

Qwen3-Coder 30B-A3B Instruct

AI model Released

Context window
262,144 tokens
Maximum output
65,536 tokens
Total parameters
30.53 B
Open weights
Yes

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

Qwen3-Coder 30B-A3B Instruct

30.53 B total parameters · qwen3_moe · BF16

Published checkpoint tensor payload: 56.9 GiB. This includes stored copies and buffers; it is separate from the runtime estimates below.

Estimated accelerator memory17.6 GiB
Weights
15.6 GiB
KV cache
0.4 GiB
Runtime allowance
1.6 GiB

One user, full model in accelerator memory.

GPUs with memory headroom

Local AI systems with memory headroom

Shared-memory systems use a planning budget of 75% of installed memory, leaving 25% for the OS and other allocations. This is an assumption, not a measured GPU allocation. Firmware and driver limits may be lower and may require configuration. Memory matches do not verify a runtime, quantized model artifact or inference speed.

Includes FP16 KV cache, prompt plus generated tokens, quantization metadata and a runtime allowance. GPU matches reserve 10% of VRAM. Memory fit is not a speed or software-compatibility guarantee; quantized weights and runtime support must be available.

API cost

USD / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Qwen3-Coder 30B-A3B Instruct

Capabilities

Context window
262,144 tokens
Maximum output
65,536 tokens
Reasoning
No
Tool calling
Yes
Open weights
Yes
Knowledge cutoff
2025-04
Model license
apache-2.0
Total parameters
30.53 B
Checkpoint tensor payload
56.87 GiB

Input modalities

  • text

Output modalities

  • text

Processing & platform

Architecture
qwen3_moe