NI

NIM 3 Coder 30B

NimGGUF by NIM-AIUpdated 2026-10-26
Download on Hugging Face
Parameters30.5B
Context40K
Layers48
Architectureqwen3moe
Smallest quant18.6 GB
Quick answer

NIM 3 Coder 30B 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. Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

NIM 3 Coder 30B – a sparse MoE model for coding and reasoning

NIM 3 Coder 30B is a 30.5‑billion‑parameter model built on a sparse Mixture‑of‑Experts architecture. It routes token predictions through dedicated experts, activating about 3 billion parameters per token. The model is packaged in GGUF format for fast local execution.

Good at

  • coding
  • reasoning
  • tools

Limits

  • trained context 40960 tokens
  • requires ~19.9 GB VRAM at 8k context
  • Apache‑2.0 license

Best for

  • software engineering tasks
  • code generation
  • debugging assistance

Who it’s for. Developers and researchers needing a lightweight yet powerful coding model. The sparse MoE design keeps latency low while delivering 30B‑class reasoning capability.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M18.6 GB 19.9 GB
Too big Get file →

The only available quant is Q4_K_M, 18.56 GB file size. It needs approximately 19.9 GB VRAM at 8k context. Use this quant if you have 20 GB or more VRAM; otherwise the model cannot run locally.

What GPU do you need for NIM 3 Coder 30B?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (18.6 GB file, about 19.9 GB in use).

Which NIM 3 Coder 30B quant should you choose?

Q4_K_M is the usual starting point for NIM 3 Coder 30B: it balances file size and quality well. Here it is a 18.6 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters30.5B (approximate, mixture of experts)
Layers48
Trained context40,960 tokens
KV cache (fp16)96 KB per token

Source

Quantized byNIM-AI
FamilyNim
Licenseapache-2.0
Downloads (HF)878
Last updated2026-10-26

Frequently asked questions about NIM 3 Coder 30B

How much VRAM does NIM 3 Coder 30B 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 NIM 3 Coder 30B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NIM 3 Coder 30B GGUF?

It depends on the quant: Q4_K_M is 18.6 GB.

What context length does NIM 3 Coder 30B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). 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 NIM 3 Coder 30B GGUF?

The files are on Hugging Face in the NIM-AI/NIM-3-Coder-30B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does NIM 3 Coder 30B 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 NIM 3 Coder 30B on 8 GB VRAM?

No. The Q4_K_M quant requires about 19.9 GB VRAM at 8k context.

Does the model support vision tasks?

No. The model is designed for text and coding only.

What license applies to this model?

Apache‑2.0.

Similar models

Browse all →

More from NIM-AI

All by NIM-AI →

More Nim models

All Nim →

Other medium models

All medium models →