AgentHorse 4B 1.0 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 3 quants, from 2.7 GB (Q4_K_M) to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
AgentHorse 4B 1.0 – a 4.21B parameter agentic model with reasoning, tools, and vision
AgentHorse 4B 1.0 is a 4.21B parameter model built on the qwen35 architecture. It merges Japanese language capabilities from Agents‑A1‑4B with coding abilities from Neohorse‑4B. The model supports reasoning, tool use, and vision tasks.
Good at
- Reasoning and planning
- Tool calling
- Vision integration
Limits
- Large context of 262144 tokens
- No license information provided
- No explicit vision limitations noted
Best for
- Building local AI assistants
- Complex task decomposition
- Multi-modal applications
Who it’s for. Developers and researchers who need a compact agentic model for local deployment. The model is suitable for those who require reasoning, tool use, and vision capabilities in a single package.
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 → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_K_M quantized file (2.71 GB, ~4.3 GB memory at 8k context). For 16 GB VRAM, the Q8_0 quantized file (4.48 GB, ~6.1 GB memory) is suitable. The BF16 variant (8.42 GB, ~10 GB memory) requires larger memory budgets.
What GPU do you need for AgentHorse 4B 1.0?
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).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).
Which AgentHorse 4B 1.0 quant should you choose?
Q4_K_M is the usual starting point for AgentHorse 4B 1.0: 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 AgentHorse 4B 1.0
How much VRAM does AgentHorse 4B 1.0 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 AgentHorse 4B 1.0 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 AgentHorse 4B 1.0 GGUF?
It depends on the quant: Q4_K_M is 2.7 GB, Q8_0 is 4.5 GB, BF16 is 8.4 GB.
What context length does AgentHorse 4B 1.0 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 AgentHorse 4B 1.0 GGUF?
The files are on Hugging Face in the CloudGoat/AgentHorse-4B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run AgentHorse 4B 1.0 on 8 GB VRAM?
Yes, the Q4_K_M quantized version is 2.71 GB and requires about 4.3 GB of VRAM at 8k context.
What quantization should I use for 16 GB VRAM?
Use the Q8_0 quantized file, 4.48 GB in size, needing roughly 6.1 GB of VRAM at 8k context.
Does this model support vision tasks?
Yes, the model has detected vision abilities and can process visual inputs.