QW

qwen3 coder 30b a3b compacted 19b 256k

QwenGGUF by continuum-aiUpdated 2026-04-11
Download on Hugging Face
Parameters19.7B
Context256K
Layers48
Architectureqwen3moe
Smallest quant12.0 GB
Quick answer

qwen3 coder 30b a3b compacted 19b 256k needs about 13.3 GB of memory at Q4_K_M (a 12.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 12.0 GB (Q4_K_M) to 20.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3-Coder 30B A3B Compact 19B 256K – 19.7B parameters, 256K context, 12 GB VRAM friendly

Qwen3-Coder-30B-A3B-Compact-19B-256K is a 19.7 B parameter model with 256 K native context. It is a mixture‑of‑experts model pruned to 35 % experts, quantized to Q4_K_M, Q5_K_M, or Q8_0 for GGUF. The model is licensed under Apache‑2.0 and supports coding, embedding, and tool‑calling.

Good at

  • Long‑context coding up to 256K tokens
  • MoE pruning for efficient inference
  • Tool‑calling and embedding tasks

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • Only non‑thinking mode

Best for

  • Local coding assistants on 12 GB GPUs
  • Repository‑scale code analysis
  • Tool‑enabled code generation

Who it’s for. Developers and researchers needing a large‑context coding model that fits in consumer GPUs. The model is suitable for local deployment via llama.cpp, Ollama, or LM Studio.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M12.0 GB 13.3 GB
Too big Get file →
Q5_K_M14.0 GB 15.3 GB
Too big Get file →
Q8_020.9 GB 22.2 GB
Too big Get file →

For 12 GB VRAM, use Q4_K_M (file size 11.96 GB, ~13.3 GB memory at 8 k context). If more VRAM is available, Q5_K_M (13.99 GB, ~15.3 GB) offers higher precision. Q8_0 (20.91 GB, ~22.2 GB) requires at least 22 GB VRAM.

What GPU do you need for qwen3 coder 30b a3b compacted 19b 256k?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q5_K_M (14.0 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (20.9 GB file, about 22.2 GB in use).

Which qwen3 coder 30b a3b compacted 19b 256k quant should you choose?

Q4_K_M is the usual starting point for qwen3 coder 30b a3b compacted 19b 256k: it balances file size and quality well. Here it is a 12.0 GB file.

The Q8_0 file is 20.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters19.7B (approximate, mixture of experts)
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bycontinuum-ai
FamilyQwen
Licenseapache-2.0
Downloads (HF)4,050
Last updated2026-04-11

Frequently asked questions about qwen3 coder 30b a3b compacted 19b 256k

How much VRAM does qwen3 coder 30b a3b compacted 19b 256k need?

About 13.3 GB at Q4_K_M with an 8K context window. That is the 12.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run qwen3 coder 30b a3b compacted 19b 256k on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of qwen3 coder 30b a3b compacted 19b 256k GGUF?

It depends on the quant: Q4_K_M is 12.0 GB, Q5_K_M is 14.0 GB, Q8_0 is 20.9 GB.

What context length does qwen3 coder 30b a3b compacted 19b 256k support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download qwen3 coder 30b a3b compacted 19b 256k GGUF?

The files are on Hugging Face in the continuum-ai/qwen3-coder-30b-a3b-compacted-19b-256k repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does qwen3 coder 30b a3b compacted 19b 256k use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

The Q4_K_M quantization requires ~13.3 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does the model support vision?

No, the model has no vision capabilities.

What context length does it support?

It natively supports 262,144 tokens and can be extended up to 1M tokens with Yarn.

Other GGUFs of Qwen3-Coder-30B-A3B-Instruct

Similar models

Browse all →

More from continuum-ai

All by continuum-ai →

More Qwen models

All Qwen →

Other medium models

All medium models →