kev 4b merged needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.3 GB (Q3_K_M) to 4.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
Kev 4B merged – a Qwen‑35 based model with reasoning, tools, and vision
Kev 4B merged is a 4.33 billion‑parameter Qwen‑35 model. It supports reasoning, tools, and vision. The model is a merge of kev‑4b with its base, eliminating the need for an adapter.
Good at
- Reasoning tasks
- Tool usage
- Vision integration
Limits
- No license specified
- Vision requires Ollama 0.35.1‑rc0 or higher
- Context limited to 262144 tokens
Best for
- Chatbot with tool calls
- Image‑based question answering
- Short‑form content generation
Who it’s for. Developers building LLM applications that need reasoning, tool use, and vision in a single model. Useful for projects that prefer a merged model over separate adapters.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 2.3 GB | 3.9 GB | Fits | Get file → | |
| Q4_K_M | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 4.6 GB | 6.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.78 GB, estimated 4.4 GB memory). For 12 GB VRAM, Q5_K_M (3.16 GB, 4.8 GB memory) is suitable. For 16 GB VRAM, Q6_K (3.56 GB, 5.2 GB memory) or Q8_0 (4.61 GB, 6.2 GB memory) can be used.
What GPU do you need for kev 4b merged?
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_M (2.3 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.6 GB file, about 6.2 GB in use).
Which kev 4b merged quant should you choose?
Q4_K_M is the usual starting point for kev 4b merged: it balances file size and quality well. Here it is a 2.8 GB file.
The Q8_0 file is 4.6 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 Q3_K_M at 2.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about kev 4b merged
How much VRAM does kev 4b merged need?
About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 kev 4b merged on an 8 GB GPU?
Yes, with Q8_0: the 4.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of kev 4b merged GGUF?
It depends on the quant: Q3_K_M is 2.3 GB, Q4_K_M is 2.8 GB, Q5_K_M is 3.2 GB, Q6_K is 3.6 GB, Q8_0 is 4.6 GB.
What context length does kev 4b merged 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 4.4 GB at 32K.
Where can I download kev 4b merged GGUF?
The files are on Hugging Face in the ayan4m1/kev-4b-merged-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Kev 4B merged on 8 GB VRAM?
Yes, using the Q4_K_M quantized file which requires about 4.4 GB of VRAM at 8k context.
Does this model support vision?
Yes, vision support is available via the provided Modelfile in Ollama 0.35.1‑rc0 or newer.
Do I need an adapter for this model?
No, the merged model includes the base model, so no adapter is required.