Deem 4B needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 0.0 GB to 4.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Deem 4B – a small English decision‑making model
Deem 4B is a 4.21B‑parameter model built on qwen35 architecture. It is optimized for text classification, routing and decision tasks with probabilities. The model is available in several GGUF quantizations for local inference.
Good at
- Reasoning
- Tool usage
- Decision classification
Limits
- No vision support
- Requires calibration for thresholds
- Limited to English
Best for
- Email triage
- Support ticket routing
- Content tagging
Who it’s for. Developers needing a lightweight local model for decision logic. The model is open‑source under apache‑2.0 and can be run with llama.cpp, Ollama or JevAlt.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.6 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (2.71 GB file, ~4.3 GB RAM at 8k context). If 12 GB VRAM is available, Q5_K_M (3.07 GB file, ~4.6 GB RAM) offers higher precision. For 16 GB VRAM or more, Q8_0 (4.48 GB file, ~6.1 GB RAM) gives the most accurate results.
What GPU do you need for Deem 4B?
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 (0.0 GB file, about 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_K_M (3.1 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
Which Deem 4B quant should you choose?
Q4_K_M is the usual starting point for Deem 4B: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 4.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
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 Deem 4B
How much VRAM does Deem 4B need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 Deem 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Deem 4B GGUF?
It depends on the quant: file is 0.0 GB, Q4_K_M is 2.7 GB, Q5_K_M is 3.1 GB, Q8_0 is 4.5 GB.
What context length does Deem 4B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Deem 4B GGUF?
The files are on Hugging Face in the mertkayacs/Deem-4B-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 Deem 4B 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 Deem 4B on 8 GB VRAM?
Yes, the Q4_K_M build uses about 4.3 GB RAM at 8k context, fitting within 8 GB VRAM.
Does Deem 4B support image inputs?
No, the model has no vision capabilities.