MiniCPM5 2B Claude Fable5 Heretic needs about 2.4 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 2.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.
MiniCPM5 2B Claude Fable5 Heretic – uncensored agent model
MiniCPM5 2B Claude Fable5 Heretic is a 2.52B parameter Llama‑based model fine‑tuned for agentic dialogue and tool use. It removes refusal guardrails via targeted weight edits, enabling multi‑step instruction following in English and Chinese. The model runs on consumer GPUs using GGUF quantizations.
Good at
- Multi‑step instruction following
- Tool and function calling
- Agentic dialogue
Limits
- No vision support
- Requires 8k context for estimates
- Apache‑2.0 license
Best for
- Local agent development
- Research on alignment and refusal mechanics
- Use cases blocked by over‑refusal
Who it’s for. Developers needing an uncensored 2B‑class tool‑using agent. Ideal for local agents, alignment research, or applications that require minimal refusal behavior.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| IQ1_S | 0.7 GB | 1.5 GB | Fits | Get file → | |
| IQ1_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| IQ2_XXS | 0.8 GB | 1.7 GB | Fits | Get file → | |
| IQ2_XS | 0.9 GB | 1.7 GB | Fits | Get file → | |
| IQ2_S | 0.9 GB | 1.8 GB | Fits | Get file → | |
| IQ2_M | 1.0 GB | 1.8 GB | Fits | Get file → | |
| Q2_K_S | 1.0 GB | 1.8 GB | Fits | Get file → | |
| Q2_K | 1.0 GB | 1.9 GB | Fits | Get file → | |
| IQ3_XXS | 1.1 GB | 1.9 GB | Fits | Get file → | |
| IQ3_XS | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_S | 1.2 GB | 2.0 GB | Fits | Get file → | |
| IQ3_S | 1.2 GB | 2.0 GB | Fits | Get file → | |
| IQ3_M | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_M | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_L | 1.4 GB | 2.2 GB | Fits | Get file → | |
| IQ4_XS | 1.4 GB | 2.3 GB | Fits | Get file → | |
| IQ4_NL | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_S | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q4_1 | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q5_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q5_K_M | 1.8 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 2.1 GB | 2.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.56 GB) or Q5_K_M (1.81 GB). If memory is tighter, IQ1_S (0.69 GB) or IQ1_M (0.73 GB) provide lower‑size options. Larger GPUs can handle Q6_K (2.07 GB) for higher quality.
What GPU do you need for MiniCPM5 2B Claude Fable5 Heretic?
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 Q6_K (2.1 GB file, about 2.9 GB in use).
Which MiniCPM5 2B Claude Fable5 Heretic quant should you choose?
Q4_K_M is the usual starting point for MiniCPM5 2B Claude Fable5 Heretic: it balances file size and quality well. Here it is a 1.6 GB file.
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
Frequently asked questions about MiniCPM5 2B Claude Fable5 Heretic
How much VRAM does MiniCPM5 2B Claude Fable5 Heretic need?
About 2.4 GB at Q4_K_M with an 8K context window. That is the 1.6 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 MiniCPM5 2B Claude Fable5 Heretic on an 8 GB GPU?
Yes, with Q6_K: the 2.1 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniCPM5 2B Claude Fable5 Heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.7 GB, IQ1_M is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.9 GB, IQ2_S is 0.9 GB and 19 more.
What context length does MiniCPM5 2B Claude Fable5 Heretic support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.4 GB at 32K.
Where can I download MiniCPM5 2B Claude Fable5 Heretic GGUF?
The files are on Hugging Face in the mradermacher/MiniCPM5-2B-Claude-Fable5-heretic-i1-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 MiniCPM5 2B Claude Fable5 Heretic 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.
Can I run this model on 8 GB VRAM?
Yes, use Q4_K_M or Q5_K_M quantizations, which fit within 8 GB VRAM plus context overhead.
Does this model support vision?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.