Midm 2.0 Mini Thinking needs about 3.7 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 2.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Midm 2.0 Mini Thinking – 2.54B parameter Korean‑centric LLM
Midm 2.0 Mini Thinking is a 2.54B parameter dense model built on the Midm family. It is optimized for reasoning and tool use in Korean contexts. The model is released under the MIT license and supports a 32,768 token context window.
Good at
- Korean reasoning
- Tool integration
- On‑device inference
Limits
- No vision support
- Requires 8,000 token context for estimates
- No external training data disclosed
Best for
- Chatbots needing Korean cultural nuance
- Lightweight local inference
- Tool‑enabled assistants
Who it’s for. Developers building Korean‑centric applications who need a compact, reasoning‑capable model. The model is suitable for local deployment on GPUs with limited VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.1 GB | Fits | Get file → | |
| IQ1_S | 0.7 GB | 2.8 GB | Fits | Get file → | |
| IQ1_M | 0.7 GB | 2.9 GB | Fits | Get file → | |
| IQ2_XXS | 0.8 GB | 2.9 GB | Fits | Get file → | |
| IQ2_XS | 0.9 GB | 3.0 GB | Fits | Get file → | |
| IQ2_S | 0.9 GB | 3.1 GB | Fits | Get file → | |
| Q2_K_S | 1.0 GB | 3.1 GB | Fits | Get file → | |
| IQ2_M | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q2_K | 1.1 GB | 3.2 GB | Fits | Get file → | |
| IQ3_XXS | 1.1 GB | 3.2 GB | Fits | Get file → | |
| IQ3_XS | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_S | 1.2 GB | 3.3 GB | Fits | Get file → | |
| IQ3_S | 1.2 GB | 3.3 GB | Fits | Get file → | |
| IQ3_M | 1.3 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_M | 1.3 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_L | 1.4 GB | 3.5 GB | Fits | Get file → | |
| IQ4_XS | 1.4 GB | 3.5 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 3.6 GB | Fits | Get file → | |
| Q4_K_S | 1.5 GB | 3.6 GB | Fits | Get file → | |
| IQ4_NL | 1.5 GB | 3.6 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 3.7 GB | Fits | Get file → | |
| Q4_1 | 1.6 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_S | 1.8 GB | 3.9 GB | Fits | Get file → | |
| Q5_K_M | 1.8 GB | 3.9 GB | Fits | Get file → | |
| Q6_K | 2.1 GB | 4.2 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S (2.8 GB memory at 8 k context). With 12 GB VRAM, Q4_K_M (3.7 GB) is a good balance. If you have 24 GB VRAM, Q6_K (4.2 GB) provides the highest quality within the size limits. Estimates are approximate.
What GPU do you need for Midm 2.0 Mini 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 Q5_K_M (1.8 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (2.1 GB file, about 4.2 GB in use).
Which Midm 2.0 Mini Thinking quant should you choose?
Q4_K_M is the usual starting point for Midm 2.0 Mini Thinking: it balances file size and quality well. Here it is a 1.6 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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 Midm 2.0 Mini Thinking
How much VRAM does Midm 2.0 Mini Thinking need?
About 3.7 GB at Q4_K_M with an 8K context window. That is the 1.6 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 Midm 2.0 Mini Thinking on an 8 GB GPU?
Yes, with Q6_K: the 2.1 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Midm 2.0 Mini Thinking GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.7 GB, IQ1_M is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.9 GB, IQ2_S is 0.9 GB and 19 more.
What context length does Midm 2.0 Mini Thinking support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Midm 2.0 Mini Thinking GGUF?
The files are on Hugging Face in the mradermacher/Midm-2.0-Mini-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 Midm 2.0 Mini 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 Midm 2.0 Mini Thinking on 8 GB VRAM?
Yes, the IQ1_S quant uses about 2.8 GB of VRAM at 8 k context, which fits within an 8 GB GPU.
Does the model support vision inputs?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the MIT license.