QW

Qwen3 Coder 30B A3B Instruct Heretic

QwenGGUF by mradermacherUpdated 2026-01-31
Download on Hugging Face
Parameters30.5B
Context256K
Layers48
Architectureqwen3moe
Smallest quant11.3 GB
Quick answer

Qwen3 Coder 30B A3B Instruct Heretic needs about 19.9 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 11.3 GB (Q2_K) to 32.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3 Coder 30B A3B Instruct Heretic – a 30.5B parameter coding model with 256K native context

Qwen3 Coder 30B A3B Instruct Heretic is a 30.5B parameter causal language model built on the Qwen3moe architecture. It supports a native context length of 262,144 tokens and is optimized for coding tasks. The model is released under the Apache‑2.0 license.

Good at

  • Coding and code generation
  • Long‑context repository understanding
  • Agentic tool‑calling

Limits

  • No vision support
  • Requires at least 8k context for memory estimates
  • No thinking mode output blocks

Best for

  • Developers needing large‑context code assistance
  • Automated coding pipelines
  • Tool‑integrated code generation

Who it’s for. Engineers and researchers who need a large‑parameter model for coding tasks and long‑context understanding. The model is suitable for local inference with GGUF support and is ideal for developers using llama.cpp, LMStudio, or similar tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K11.3 GB 12.6 GB
Too big Get file →
Q3_K_S13.3 GB 14.6 GB
Too big Get file →
Q3_K_M14.7 GB 16.0 GB
Too big Get file →
Q3_K_L15.9 GB 17.2 GB
Too big Get file →
IQ4_XS16.6 GB 17.9 GB
Too big Get file →
Q4_K_S17.5 GB 18.8 GB
Too big Get file →
Q4_K_M18.6 GB 19.9 GB
Too big Get file →
Q5_K_S21.1 GB 22.4 GB
Too big Get file →
Q5_K_M21.7 GB 23.0 GB
Too big Get file →
Q6_K25.1 GB 26.4 GB
Too big Get file →
Q8_032.5 GB 33.8 GB
Too big Get file →

For 8GB VRAM, use Q4_K_S (file size 17.46 GB, estimated memory 18.8 GB). For 12GB VRAM, Q3_K_M (14.71 GB, 16 GB memory) is a good balance. If you have 16GB VRAM, Q4_K_M (18.56 GB, 19.9 GB memory) provides higher quality while staying within limits. Estimates are approximate.

What GPU do you need for Qwen3 Coder 30B A3B Instruct Heretic?

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 Q3_K_M (14.7 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (21.7 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (25.1 GB file, about 26.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (32.5 GB file, about 33.8 GB in use).

Which Qwen3 Coder 30B A3B Instruct Heretic quant should you choose?

Q4_K_M is the usual starting point for Qwen3 Coder 30B A3B Instruct Heretic: it balances file size and quality well. Here it is a 18.6 GB file.

The Q8_0 file is 32.5 GB, about 1.8 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.

If memory is tight, the smallest file is Q2_K at 11.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters30.5B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)4,982
Last updated2026-01-31

Frequently asked questions about Qwen3 Coder 30B A3B Instruct Heretic

How much VRAM does Qwen3 Coder 30B A3B Instruct Heretic need?

About 19.9 GB at Q4_K_M with an 8K context window. That is the 18.6 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 Instruct Heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3 Coder 30B A3B Instruct Heretic GGUF?

It depends on the quant: Q2_K is 11.3 GB, Q3_K_S is 13.3 GB, Q3_K_M is 14.7 GB, Q3_K_L is 15.9 GB, IQ4_XS is 16.6 GB, Q4_K_S is 17.5 GB and 5 more.

What context length does Qwen3 Coder 30B A3B Instruct Heretic 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 Instruct Heretic GGUF?

The files are on Hugging Face in the mradermacher/Qwen3-Coder-30B-A3B-Instruct-Heretic-GGUF 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 Instruct Heretic 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?

Use the Q4_K_S quant, which estimates 18.8 GB memory at 8k context. It may fit with memory optimizations but is close to the limit.

Does this model support vision tasks?

No, the model has no vision capabilities.

What context length does it natively support?

The model natively supports 262,144 tokens, extendable up to 1M tokens with Yarn.

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

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →