plumb 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 2 quants, from 2.7 GB (Q4_K_M) to 4.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Plumb‑4B: a 4.2B parameter decision model for probability outputs
Plumb‑4B is a 4.2B parameter decision model built on the qwen35 architecture. It returns probabilities for up to 16 options in a single forward pass, with no token generation. The model is trained on hard decisions and calibrated with temperature T = 2.07.
Good at
- Fast single‑pass probability inference
- Decision‑making without token generation
- Calibration for JevBench scoring
Limits
- No vision support
- Requires a CUDA GPU with ~10 GB free (bf16)
- No chat or text generation capabilities
Best for
- Evaluating multiple‑choice questions
- Generating probability distributions for decision tasks
- Benchmarking decision models
Who it’s for. Engineers and researchers needing quick, calibrated probability outputs for decision tasks. It is suitable for integration into services that require deterministic probability estimates without text generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → |
For 8 k context, Q4_K_M uses 2.71 GB and needs about 4.3 GB VRAM. Q8_0 uses 4.48 GB and needs about 6.1 GB VRAM. Choose Q4_K_M for tighter VRAM budgets, Q8_0 for higher precision.
What GPU do you need for plumb 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_M (2.7 GB file, about 4.3 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 plumb 4b quant should you choose?
Q4_K_M is the usual starting point for plumb 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about plumb 4b
How much VRAM does plumb 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 plumb 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 plumb 4b GGUF?
It depends on the quant: Q4_K_M is 2.7 GB, Q8_0 is 4.5 GB.
What context length does plumb 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 plumb 4b GGUF?
The files are on Hugging Face in the crh225/plumb-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 plumb 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 Plumb‑4B on 8 GB VRAM?
Q4_K_M requires about 4.3 GB VRAM at 8 k context, so 8 GB is sufficient. Q8_0 needs about 6.1 GB, also within 8 GB.
Does Plumb‑4B support text generation?
No. It is a decision model that outputs probabilities for options without generating text.
What license applies to Plumb‑4B?
The model is released under the Apache‑2.0 license.