Melinoe GLM 30B A3B Thinking needs about 19.5 GB of memory at Q4_K_M (a 18.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.1 GB to 24.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
Melinoe GLM 30B A3B Thinking – a 30B parameter LLM focused on empathetic conversation
Melinoe GLM 30B A3B Thinking is a 29.9 billion parameter model built on the GLM family and deepseek2 architecture. It is fine‑tuned for reasoning and tool use, with a 202 752 token context window. The model is released under the MIT license.
Good at
- Reasoning and tool use
- Empathetic dialogue
- Creative brainstorming
Limits
- No vision support
- Requires 8 k context for memory estimates
- Not suitable for medical or legal advice
Best for
- Companionship and emotional support
- Creative writing and brainstorming
- Role‑playing scenarios
Who it’s for. Developers and researchers who need a conversational partner capable of reasoning and tool integration. The model is intended for mature audiences and should not replace professional advice.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 6.2 GB | 7.5 GB | Tight | Get file → | |
| IQ1_M | 6.9 GB | 8.2 GB | Too big | Get file → | |
| IQ2_XXS | 8.0 GB | 9.3 GB | Too big | Get file → | |
| IQ2_XS | 8.9 GB | 10.2 GB | Too big | Get file → | |
| IQ2_S | 9.0 GB | 10.4 GB | Too big | Get file → | |
| IQ2_M | 9.9 GB | 11.2 GB | Too big | Get file → | |
| Q2_K_S | 10.2 GB | 11.6 GB | Too big | Get file → | |
| Q2_K | 11.0 GB | 12.4 GB | Too big | Get file → | |
| IQ3_XXS | 11.6 GB | 13.0 GB | Too big | Get file → | |
| IQ3_XS | 12.3 GB | 13.7 GB | Too big | Get file → | |
| IQ3_S | 13.0 GB | 14.4 GB | Too big | Get file → | |
| Q3_K_S | 13.0 GB | 14.4 GB | Too big | Get file → | |
| IQ3_M | 13.2 GB | 14.5 GB | Too big | Get file → | |
| Q3_K_M | 14.4 GB | 15.7 GB | Too big | Get file → | |
| Q3_K_L | 15.6 GB | 16.9 GB | Too big | Get file → | |
| IQ4_XS | 16.0 GB | 17.4 GB | Too big | Get file → | |
| Q4_0 | 17.0 GB | 18.3 GB | Too big | Get file → | |
| Q4_K_S | 17.1 GB | 18.4 GB | Too big | Get file → | |
| Q4_K_M | 18.1 GB | 19.5 GB | Too big | Get file → | |
| Q4_1 | 18.8 GB | 20.1 GB | Too big | Get file → | |
| Q5_K_S | 20.7 GB | 22.0 GB | Too big | Get file → | |
| Q5_K_M | 21.3 GB | 22.6 GB | Too big | Get file → | |
| Q6_K | 24.6 GB | 26.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (6.2 GB file, 7.5 GB memory at 8 k context). For 12 GB VRAM, IQ2_XS (8.87 GB file, 10.2 GB memory) or Q2_K (11.04 GB file, 12.4 GB memory). For 16 GB VRAM, Q4_K_M (18.13 GB file, 19.5 GB memory) or Q5_K_S (20.66 GB file, 22 GB memory).
What GPU do you need for Melinoe GLM 30B A3B Thinking?
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: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
- 8 GB VRAM: the best quant that fits is IQ1_S (6.2 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K_S (10.2 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_M (14.4 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (21.3 GB file, about 22.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (24.6 GB file, about 26.0 GB in use).
Which Melinoe GLM 30B A3B Thinking quant should you choose?
Q4_K_M is the usual starting point for Melinoe GLM 30B A3B Thinking: it balances file size and quality well. Here it is a 18.1 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Melinoe GLM 30B A3B Thinking
How much VRAM does Melinoe GLM 30B A3B Thinking need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 18.1 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 Melinoe GLM 30B A3B Thinking on an 8 GB GPU?
Yes, with IQ1_S: the 6.2 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Melinoe GLM 30B A3B Thinking GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 6.2 GB, IQ1_M is 6.9 GB, IQ2_XXS is 8.0 GB, IQ2_XS is 8.9 GB, IQ2_S is 9.0 GB and 18 more.
What context length does Melinoe GLM 30B A3B Thinking support?
The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.4 GB at 32K.
Where can I download Melinoe GLM 30B A3B Thinking GGUF?
The files are on Hugging Face in the mradermacher/Melinoe-GLM-30B-A3B-Thinking-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 Melinoe GLM 30B A3B Thinking use?
Hugging Face lists the license as mit. 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 Melinoe on 8 GB VRAM?
Yes, the IQ1_S quant uses 6.2 GB file size and requires about 7.5 GB memory at 8 k context.
Does the model support image input?
No, the model has no vision capability.
Is the model licensed for commercial use?
The model is released under the MIT license, which allows commercial use.