HAI_Medicare 120B_v3 needs about 234.9 GB of memory at F16 (a 233.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
HAI_Medicare 120B_v3 is a 117B-parameter Hai model in GGUF format, quantized by HongKi08. Its trained context length is 128K tokens. The repository has 1 quant file, from 233.8 GB (F16) to 233.8 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 233.8 GB | 234.9 GB | Too big | Get file → |
What GPU do you need for HAI_Medicare 120B_v3?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which HAI_Medicare 120B_v3 quant should you choose?
F16 (233.8 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 HAI_Medicare 120B_v3
How much VRAM does HAI_Medicare 120B_v3 need?
About 234.9 GB at F16 with an 8K context window. That is the 233.8 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 HAI_Medicare 120B_v3 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 234.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of HAI_Medicare 120B_v3 GGUF?
It depends on the quant: F16 is 233.8 GB.
What context length does HAI_Medicare 120B_v3 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.
Where can I download HAI_Medicare 120B_v3 GGUF?
The files are on Hugging Face in the HongKi08/HAI_Medicare-120B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.