Ezjev 4b S2 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.
Ezjev 4b S2 – a 4.21B parameter Qwen3.5‑style decision model
Ezjev 4b S2 is a 4.21B parameter typed‑decision model based on Qwen3.5. It supports vision inputs and was trained with LoRA fine‑tuning on a wide range of decision tasks. The model is available in multiple GGUF quantizations.
Good at
- Typed decision tasks
- Vision‑enabled reasoning
- Low‑latency inference on GPUs
Limits
- Large context length of 262144 tokens
- High VRAM requirement for full precision
- No support for text‑only fine‑tuning
Best for
- Decision‑making applications
- Vision‑based question answering
- Low‑latency inference on RTX GPUs
Who it’s for. Developers building decision‑oriented AI services that require vision support and fast inference. The model is suitable for production use on GPUs with sufficient VRAM.
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_S (size 2.56 GB, ~4.1 GB RAM). For 12 GB VRAM, Q5_K_S (size 2.99 GB, ~4.6 GB RAM). For 16 GB VRAM, Q6_K (size 3.46 GB, ~5 GB RAM). Estimates are approximate.
What GPU do you need for Ezjev 4b S2?
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 Ezjev 4b S2 quant should you choose?
Q4_K_M is the usual starting point for Ezjev 4b S2: 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 Ezjev 4b S2
How much VRAM does Ezjev 4b S2 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 Ezjev 4b S2 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 Ezjev 4b S2 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 Ezjev 4b S2 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 Ezjev 4b S2 GGUF?
The files are on Hugging Face in the mradermacher/ezjev-4b-s2-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 Ezjev 4b S2 use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Does the model support vision?
Yes, the model has detected vision ability and can process image inputs.
What is the maximum context length?
The model was trained with 262144 tokens and supports that full context length.