Ollama_Model_16Kobs_16Bit needs about 7.9 GB of memory at F16 (a 6.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Ollama_Model_16Kobs_16Bit is a 3.21B-parameter Ollama model in GGUF format, quantized by zzzzhhhh3413. Its trained context length is 128K tokens. The repository has 1 quant file, from 6.4 GB (F16) to 6.4 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 6.4 GB | 7.9 GB | Tight | Get file → |
What GPU do you need for Ollama_Model_16Kobs_16Bit?
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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is F16 (6.4 GB file, about 7.9 GB in use).
Which Ollama_Model_16Kobs_16Bit quant should you choose?
F16 (6.4 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ollama_Model_16Kobs_16Bit
How much VRAM does Ollama_Model_16Kobs_16Bit need?
About 7.9 GB at F16 with an 8K context window. That is the 6.4 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 Ollama_Model_16Kobs_16Bit on an 8 GB GPU?
Yes, with F16: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ollama_Model_16Kobs_16Bit GGUF?
It depends on the quant: F16 is 6.4 GB.
What context length does Ollama_Model_16Kobs_16Bit support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Ollama_Model_16Kobs_16Bit GGUF?
The files are on Hugging Face in the zzzzhhhh3413/ollama_model_16kobs_16bit repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Ollama_Model_16Kobs_16Bit 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.