MI

MilkDropLM 32b v0.3 i1

MilkdroplmGGUF by mradermacherUpdated 2025-02-26
Download on Hugging Face
Parameters32.8B
Context32K
Layers64
Architectureqwen2
Smallest quant7.3 GB
Quick answer

MilkDropLM 32b v0.3 i1 needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 7.3 GB (IQ1_S) to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

MilkDropLM 32b v0.3 i1 – a 32.8B Qwen2 language model for MilkDrop preset creation

MilkDropLM 32b v0.3 i1 is a 32.8B parameter model based on Qwen2.5-Coder-32B-Instruct. It is fine‑tuned for generating and upgrading MilkDrop presets with a maximum context length of 32768 tokens. The model is released under the Apache‑2.0 license.

Good at

  • Generating MilkDrop presets
  • Upgrading 7b presets
  • Conversational preset editing

Limits

  • Requires 16k context for preset upgrade
  • No vision support
  • Large VRAM needed for higher quants

Best for

  • MilkDrop preset authors
  • Preset upgrade workflows
  • Creative visual scripting

Who it’s for. Artists and developers who create or modify MilkDrop visualizations. The model supports natural language prompts for preset generation and editing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.3 GB 9.9 GB
Too big Get file →
IQ1_M7.9 GB 10.6 GB
Too big Get file →
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.4 GB 13.0 GB
Too big Get file →
IQ2_M11.3 GB 13.9 GB
Too big Get file →
Q2_K_S11.5 GB 14.1 GB
Too big Get file →
Q2_K12.3 GB 15.0 GB
Too big Get file →
IQ3_XXS12.8 GB 15.5 GB
Too big Get file →
IQ3_XS13.7 GB 16.4 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.4 GB 17.1 GB
Too big Get file →
IQ3_M14.8 GB 17.5 GB
Too big Get file →
Q3_K_M15.9 GB 18.6 GB
Too big Get file →
Q3_K_L17.2 GB 19.9 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.7 GB 21.4 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.9 GB 22.5 GB
Too big Get file →
Q4_120.6 GB 23.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.3 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →

For 8–12 GB VRAM, use IQ1_S (7.27 GB) or IQ1_M (7.93 GB). For 12–16 GB VRAM, IQ2_XS (9.96 GB) or IQ2_S (10.39 GB) are suitable. For 16–20 GB VRAM, Q3_K_S (14.39 GB) or IQ3_S (14.44 GB) provide a balance of size and quality. Memory estimates are approximate.

What GPU do you need for MilkDropLM 32b v0.3 i1?

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: the best quant that fits is IQ2_XXS (9.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (12.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).

Which MilkDropLM 32b v0.3 i1 quant should you choose?

Q4_K_M is the usual starting point for MilkDropLM 32b v0.3 i1: it balances file size and quality well. Here it is a 19.9 GB file.

If memory is tight, the smallest file is IQ1_S at 7.3 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

Architectureqwen2
Parameters32.8B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)925
Last updated2025-02-26

Frequently asked questions about MilkDropLM 32b v0.3 i1

How much VRAM does MilkDropLM 32b v0.3 i1 need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 MilkDropLM 32b v0.3 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MilkDropLM 32b v0.3 i1 GGUF?

It depends on the quant: IQ1_S is 7.3 GB, IQ1_M is 7.9 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.4 GB, IQ2_M is 11.3 GB and 17 more.

What context length does MilkDropLM 32b v0.3 i1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download MilkDropLM 32b v0.3 i1 GGUF?

The files are on Hugging Face in the mradermacher/MilkDropLM-32b-v0.3-i1-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 MilkDropLM 32b v0.3 i1 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 MilkDropLM 32b v0.3 i1 on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quant files, which are 7.27 GB and 7.93 GB respectively, will fit within 8 GB VRAM with some headroom.

Does the model support image generation?

No, MilkDropLM 32b v0.3 i1 does not have vision or image generation capabilities.

What context length is required to upgrade a 7b preset?

At least 16k context tokens are required to use the preset upgrade feature.

Other GGUFs of MilkDropLM-32b-v0.3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Milkdroplm models

All Milkdroplm →

Other medium models

All medium models →