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 12 quants, from 1.9 GB (Q2_K) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Deem 4B – a 4.21B parameter Qwen‑35 model for local decision making
Deem 4B is a 4.21B parameter model built on the Qwen‑35 architecture. It is optimized for text classification, routing and decision tasks with probability outputs. The model is released under the apache‑2.0 license.
Good at
- Reasoning and decision logic
- Tool usage and API integration
- Vision support for local inference
Limits
- No vision support beyond basic image classification
- Requires 8k context for full accuracy
- No multi‑expert architecture
Best for
- Local decision engines
- Decision‑aware chatbots
- Probabilistic routing systems
Who it’s for. Developers building lightweight local inference services that need accurate decision probabilities. The model is suitable for applications requiring quick, on‑device reasoning and tool calling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.9 GB | 3.5 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_L | 2.4 GB | 4.0 GB | Fits | Get file → | |
| IQ4_XS | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_S | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.6 GB | Fits | Get file → | |
| Q6_K | 3.5 GB | 5.0 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → | |
| F16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (2.71 GB file, ~4.3 GB RAM at 8k context). For 4 GB VRAM, Q3_K_S (2.07 GB file, ~3.6 GB RAM). For 2 GB VRAM, Q2_K (1.92 GB file, ~3.5 GB RAM). Estimates are approximate.
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 Q3_K_L (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.4 GB file, about 10.0 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 Q2_K at 1.9 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
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: Q2_K is 1.9 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, IQ4_XS is 2.5 GB, Q4_K_S is 2.6 GB and 6 more.
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 mradermacher/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 quant uses about 4.3 GB RAM at 8k context, which fits within 8 GB VRAM with headroom.
Does Deem 4B support vision tasks?
It has basic vision support but is primarily designed for text classification and decision tasks.