Tev1 4B Experimental 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 8 quants, from 2.3 GB (Q3_K_M) to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
4B decision model that selects one option from a structured prompt
Tev1 4B Experimental is a 4.21‑billion‑parameter decision model. It is a supervised fine‑tune of Qwen3.5‑4B that chooses a single option from a structured state, question, and list of 2–24 labeled choices. The model retains a standard next‑token head and is not intended for generic chat.
Good at
- Selecting a single option from structured prompts
- High accuracy on internal decision sets
- Fast inference with low‑precision quantization
Limits
- Not designed for general chat
- No vision support
- Requires careful prompt formatting
Best for
- Decision‑making assistants
- Structured Q&A bots
- Policy‑transfer evaluation
Who it’s for. Developers building decision‑oriented assistants that need a single‑letter output. The model is suitable for applications that can provide a JSON payload with state, question, and options and expect a deterministic choice.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_L | 2.4 GB | 4.0 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 → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (est. 4.3 GB). For 6 GB VRAM use Q4_K_S (est. 4.1 GB). For 4 GB VRAM use Q3_K_M (est. 3.8 GB).
What GPU do you need for Tev1 4B Experimental?
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 Q6_K (3.5 GB file, about 5.0 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).
Which Tev1 4B Experimental quant should you choose?
Q4_K_M is the usual starting point for Tev1 4B Experimental: it balances file size and quality well. Here it is a 2.7 GB file.
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 Tev1 4B Experimental
How much VRAM does Tev1 4B Experimental 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 Tev1 4B Experimental on an 8 GB GPU?
Yes, with Q6_K: the 3.5 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Tev1 4B Experimental GGUF?
It depends on the quant: Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, Q4_K_S is 2.6 GB, Q4_K_M is 2.7 GB, Q5_K_S is 3.0 GB, Q5_K_M is 3.1 GB and 2 more.
What context length does Tev1 4B Experimental 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 Tev1 4B Experimental GGUF?
The files are on Hugging Face in the prithivMLmods/Tev1-4B-experimental-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 Tev1 4B Experimental 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 Tev1 4B Experimental on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 4.3 GB of VRAM at 8 k context, which fits within an 8 GB budget.
Does the model support vision inputs?
No, the model is a text‑only decision model and has no vision capability.
What license applies to the fine‑tuned weights?
The base Qwen3.5‑4B is Apache‑2.0; the fine‑tuned weights are under a license that is still being finalized.