HybridAgent 14B Agentic needs about 11.2 GB of memory at Q4_K_M (a 9.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 0.0 GB to 29.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
HybridAgent 14B Agentic – a Qwen3‑based LLM for agentic reasoning
HybridAgent 14B Agentic is a 14.8 billion‑parameter model built on Qwen3. It combines latent reasoning with text‑based tool use, enabling dynamic navigation between internal thoughts and external actions. The model supports up to 32 768 context tokens and is released under the MIT license.
Good at
- Latent reasoning with HybridLink
- Tool‑based actions via Python and web search
- Continuous text generation in a single pass
Limits
- No vision support
- Requires llama.cpp b11716 or newer
- Large memory footprint for higher precision quants
Best for
- Agentic task automation
- Multi‑turn tool‑using dialogue
- Complex reasoning workflows
Who it’s for. Developers building agentic applications that need both internal reasoning and external tool calls. Researchers testing hybrid latent‑text generation models. Users who prefer open‑source models with MIT licensing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.9 GB | Fits | Get file → | |
| IQ2_S | 5.1 GB | 6.9 GB | Fits | Get file → | |
| IQ2_M | 5.6 GB | 7.4 GB | Tight | Get file → | |
| Q2_K | 5.8 GB | 7.6 GB | Tight | Get file → | |
| IQ3_XXS | 6.6 GB | 8.4 GB | Too big | Get file → | |
| Q3_K_S | 6.9 GB | 8.7 GB | Too big | Get file → | |
| IQ3_XS | 6.9 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_M | 7.2 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_L | 7.6 GB | 9.4 GB | Too big | Get file → | |
| IQ3_M | 8.0 GB | 9.9 GB | Too big | Get file → | |
| IQ4_XS | 8.4 GB | 10.2 GB | Too big | Get file → | |
| Q4_0 | 8.7 GB | 10.5 GB | Too big | Get file → | |
| Q4_K_S | 8.9 GB | 10.7 GB | Too big | Get file → | |
| IQ4_NL | 9.3 GB | 11.1 GB | Too big | Get file → | |
| Q4_K_M | 9.3 GB | 11.2 GB | Too big | Get file → | |
| Q4_1 | 9.5 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_L | 10.0 GB | 11.9 GB | Too big | Get file → | |
| Q5_K_S | 10.6 GB | 12.4 GB | Too big | Get file → | |
| Q5_K_M | 11.2 GB | 13.0 GB | Too big | Get file → | |
| Q6_K_S | 12.4 GB | 14.2 GB | Too big | Get file → | |
| Q6_K | 12.9 GB | 14.8 GB | Too big | Get file → | |
| Q6_K_L | 13.5 GB | 15.4 GB | Too big | Get file → | |
| Q8_0 | 15.7 GB | 17.5 GB | Too big | Get file → | |
| BF16 | 29.5 GB | 31.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (9.32 GB) or Q4_K_S (8.86 GB). For 12 GB VRAM, Q5_K_S (10.58 GB) or Q5_K_M (11.19 GB) are suitable. Higher precision quants like Q6_K (12.91 GB) or Q8_0 (15.7 GB) require more memory but offer better quality. Estimates are approximate.
What GPU do you need for HybridAgent 14B Agentic?
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 the main file (0.0 GB file, about 1.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K (5.8 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_L (10.0 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K_L (13.5 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.7 GB file, about 17.5 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (29.5 GB file, about 31.4 GB in use).
Which HybridAgent 14B Agentic quant should you choose?
Q4_K_M is the usual starting point for HybridAgent 14B Agentic: it balances file size and quality well. Here it is a 9.3 GB file.
The Q8_0 file is 15.7 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.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about HybridAgent 14B Agentic
How much VRAM does HybridAgent 14B Agentic need?
About 11.2 GB at Q4_K_M with an 8K context window. That is the 9.3 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 HybridAgent 14B Agentic on an 8 GB GPU?
Yes, with Q2_K: the 5.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of HybridAgent 14B Agentic GGUF?
It depends on the quant: file is 0.0 GB, IQ2_S is 5.1 GB, IQ2_M is 5.6 GB, Q2_K is 5.8 GB, IQ3_XXS is 6.6 GB, Q3_K_S is 6.9 GB and 18 more.
What context length does HybridAgent 14B Agentic support?
The GGUF header lists a trained context length of 32,768 tokens (32K). 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 HybridAgent 14B Agentic GGUF?
The files are on Hugging Face in the bartowski/togethercomputer_HybridAgent-14B-Agentic-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 HybridAgent 14B Agentic use?
Hugging Face lists the license as mit. 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 HybridAgent 14B Agentic on 8 GB VRAM?
Yes, using the Q4_K_M quant (9.32 GB) or Q4_K_S (8.86 GB) will fit within 8 GB VRAM with some headroom.
Does this model support image inputs?
No, HybridAgent 14B Agentic only accepts text input.
What is the maximum context length?
The model supports up to 32 768 context tokens.