tpn004 cand v1f aim needs about 16.5 GB of memory at its main file (a 14.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
24‑billion‑parameter Mistral‑3 model, 131072‑token context
tpn004 cand v1f aim is a 24‑billion‑parameter Mistral‑3 architecture model. It supports a 131072‑token context window and is available in a single GGUF file. The file size is 14.67 GB, requiring approximately 16.5 GB of VRAM at 8 k context.
Good at
- Large context reasoning
- High‑capacity language modeling
- Long‑form text generation
Limits
- No quantization options listed
- Requires ~16.5 GB VRAM at 8 k context
- License information not provided
Best for
- Research on long‑context language tasks
- Generating extensive documents
- Testing Mistral‑3 capabilities
Who it’s for. Researchers and developers needing a large‑parameter Mistral‑3 model with extensive context. Suitable for environments with high VRAM capacity.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.7 GB | 16.5 GB | Too big | Get file → |
Only the default GGUF file is available, with an estimated 16.5 GB VRAM requirement at 8 k context. No alternative quantizations are listed, so use the provided file as is.
What GPU do you need for tpn004 cand v1f aim?
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: the best quant that fits is the main file (14.7 GB file, about 16.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about tpn004 cand v1f aim
How much VRAM does tpn004 cand v1f aim need?
About 16.5 GB at its main file with an 8K context window. That is the 14.7 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 tpn004 cand v1f aim on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of tpn004 cand v1f aim GGUF?
It depends on the quant: file is 14.7 GB.
What context length does tpn004 cand v1f aim support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download tpn004 cand v1f aim GGUF?
The files are on Hugging Face in the tatjr13/tpn004-cand-v1f-aim repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
No, the model requires about 16.5 GB of VRAM at 8 k context, so 8 GB is insufficient.
What context length does this model support?
It supports up to 131072 tokens, allowing very long context processing.
Are there any quantized versions available?
Only the default GGUF file is provided; no other quantizations are listed.