Mordant 7B Think needs about 9.3 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 6.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.
Mordant 7B Think – a fine‑tuned OLMo model for spatial reasoning in image prompt generation
Mordant 7B Think is a 7.3 billion parameter model fine‑tuned on 7,203 detailed compositions. It excels at chain‑of‑thought reasoning and spatially structured prompt creation. The model is trained with a "sharp, caustic, professional mentor" personality during reasoning.
Good at
- Spatially structured image prompt generation
- Chain‑of‑thought reasoning
- Compositional depth enhancement
Limits
- No vision support
- Requires ChatML format
- License is apache‑2.0
Best for
- Generating detailed image prompts from short descriptions
- Enhancing existing prompts with compositional depth
- Infusing specific art styles into compositions
Who it’s for. Developers and artists who need structured, reasoning‑based image prompts. The model is suitable for local inference using GGUF files in llama.cpp, LM Studio, or Comfy‑UI.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 4.8 GB | Fits | Get file → | |
| IQ1_S | 1.8 GB | 6.6 GB | Fits | Get file → | |
| IQ1_M | 1.9 GB | 6.7 GB | Fits | Get file → | |
| IQ2_XXS | 2.1 GB | 6.9 GB | Fits | Get file → | |
| IQ2_XS | 2.3 GB | 7.1 GB | Fits | Get file → | |
| IQ2_S | 2.5 GB | 7.3 GB | Tight | Get file → | |
| Q2_K_S | 2.6 GB | 7.4 GB | Tight | Get file → | |
| IQ2_M | 2.7 GB | 7.5 GB | Tight | Get file → | |
| Q2_K | 2.9 GB | 7.7 GB | Tight | Get file → | |
| IQ3_XXS | 2.9 GB | 7.7 GB | Tight | Get file → | |
| IQ3_XS | 3.1 GB | 7.9 GB | Tight | Get file → | |
| IQ3_S | 3.3 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_S | 3.3 GB | 8.1 GB | Too big | Get file → | |
| IQ3_M | 3.5 GB | 8.3 GB | Too big | Get file → | |
| Q3_K_M | 3.7 GB | 8.4 GB | Too big | Get file → | |
| Q3_K_L | 4.0 GB | 8.7 GB | Too big | Get file → | |
| IQ4_XS | 4.0 GB | 8.8 GB | Too big | Get file → | |
| IQ4_NL | 4.2 GB | 9.0 GB | Too big | Get file → | |
| Q4_0 | 4.2 GB | 9.0 GB | Too big | Get file → | |
| Q4_K_S | 4.2 GB | 9.0 GB | Too big | Get file → | |
| Q4_K_M | 4.5 GB | 9.3 GB | Too big | Get file → | |
| Q4_1 | 4.6 GB | 9.4 GB | Too big | Get file → | |
| Q5_K_S | 5.1 GB | 9.9 GB | Too big | Get file → | |
| Q5_K_M | 5.2 GB | 10.0 GB | Too big | Get file → | |
| Q6_K | 6.0 GB | 10.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (1.82 GB file, 6.6 GB memory). For 12 GB VRAM, IQ2_S (2.51 GB file, 7.3 GB memory) or Q2_K (2.86 GB file, 7.7 GB memory). For 16 GB VRAM, Q4_K_M (4.47 GB file, 9.3 GB memory) offers a balance of size and performance. Estimates are approximate.
What GPU do you need for Mordant 7B Think?
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: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XS (3.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 10.8 GB in use).
Which Mordant 7B Think quant should you choose?
Q4_K_M is the usual starting point for Mordant 7B Think: it balances file size and quality well. Here it is a 4.5 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 Mordant 7B Think
How much VRAM does Mordant 7B Think need?
About 9.3 GB at Q4_K_M with an 8K context window. That is the 4.5 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 Mordant 7B Think on an 8 GB GPU?
Yes, with IQ3_XS: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mordant 7B Think GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.8 GB, IQ1_M is 1.9 GB, IQ2_XXS is 2.1 GB, IQ2_XS is 2.3 GB, IQ2_S is 2.5 GB and 19 more.
What context length does Mordant 7B Think support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.
Where can I download Mordant 7B Think GGUF?
The files are on Hugging Face in the mradermacher/Mordant-7B-Think-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 Mordant 7B Think 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 Mordant 7B Think on 8 GB VRAM?
Yes, the IQ1_S quant uses about 6.6 GB of VRAM at 8 k context, which fits within an 8 GB budget.
Does the model support image generation directly?
No, it generates text prompts for image generation; it does not produce images itself.
What format is required for inference?
The model uses ChatML format with a pre‑seeded block; a minimal system prompt is recommended for consistency.