MI

Minicpm 2B Zero Refusal

MiniCPMGGUF by mradermacherUpdated 2026-09-21
Download on Hugging Face
Parameters2.52B
Context128K
Layers42
Architecturellama
Smallest quant0.0 GB
Quick answer

Minicpm 2B Zero Refusal 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.

MiniCPM 2B Zero Refusal – 2.52B parameter model fine‑tuned to avoid mid‑refusals

MiniCPM 2B Zero Refusal is a 2.52B parameter llama‑based model trained on 75,000 uncensored examples to reduce mid‑refusals. It supports internal reasoning and follows the ChatML format. The model is available in multiple GGUF quantizations.

Good at

  • Reasoning
  • Tool usage
  • Full‑context completion

Limits

  • No vision support
  • License not specified
  • Large context requires 131072 tokens

Best for

  • Chatbot development
  • Tool‑integrated assistants
  • Long‑form content generation

Who it’s for. Developers building conversational agents that need consistent responses without mid‑refusal. Researchers testing reasoning and tool‑use capabilities in a small‑parameter model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ1_S0.7 GB 1.5 GB
Fits Get file →
IQ1_M0.7 GB 1.6 GB
Fits Get file →
IQ2_XXS0.8 GB 1.7 GB
Fits Get file →
IQ2_XS0.9 GB 1.7 GB
Fits Get file →
IQ2_S0.9 GB 1.8 GB
Fits Get file →
IQ2_M1.0 GB 1.8 GB
Fits Get file →
Q2_K_S1.0 GB 1.8 GB
Fits Get file →
Q2_K1.0 GB 1.9 GB
Fits Get file →
IQ3_XXS1.1 GB 1.9 GB
Fits Get file →
IQ3_XS1.1 GB 2.0 GB
Fits Get file →
Q3_K_S1.2 GB 2.0 GB
Fits Get file →
IQ3_S1.2 GB 2.0 GB
Fits Get file →
IQ3_M1.2 GB 2.1 GB
Fits Get file →
Q3_K_M1.3 GB 2.1 GB
Fits Get file →
Q3_K_L1.4 GB 2.2 GB
Fits Get file →
IQ4_XS1.4 GB 2.3 GB
Fits Get file →
IQ4_NL1.5 GB 2.3 GB
Fits Get file →
Q4_01.5 GB 2.3 GB
Fits Get file →
Q4_K_S1.5 GB 2.4 GB
Fits Get file →
Q4_K_M1.6 GB 2.4 GB
Fits Get file →
Q4_11.6 GB 2.5 GB
Fits Get file →
Q5_K_S1.8 GB 2.6 GB
Fits Get file →
Q5_K_M1.8 GB 2.7 GB
Fits Get file →
Q6_K2.1 GB 2.9 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (0.69 GB, 1.5 GB RAM) or IQ1_M (0.73 GB, 1.6 GB RAM). If 12 GB VRAM is available, Q4_K_M (1.56 GB, 2.4 GB RAM) offers a good balance of size and performance. Larger quants like Q6_K need more than 16 GB VRAM.

What GPU do you need for Minicpm 2B Zero Refusal?

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 Minicpm 2B Zero Refusal quant should you choose?

Q4_K_M is the usual starting point for Minicpm 2B Zero Refusal: 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

Architecturellama
Parameters2.52B
Layers42
Trained context131,072 tokens
KV cache (fp16)42 KB per token

Source

Quantized bymradermacher
FamilyMiniCPM
Downloads (HF)619
Last updated2026-09-21

Frequently asked questions about Minicpm 2B Zero Refusal

How much VRAM does Minicpm 2B Zero Refusal 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 Minicpm 2B Zero Refusal 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 Minicpm 2B Zero Refusal 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 Minicpm 2B Zero Refusal 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 Minicpm 2B Zero Refusal GGUF?

The files are on Hugging Face in the mradermacher/Minicpm-2B-Zero-Refusal-i1-GGUF 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?

Yes, the IQ1_S and IQ1_M quantizations fit within 8 GB VRAM, using approximately 1.5–1.6 GB of RAM at 8 k context.

Does this model support vision?

No, the model does not have vision capabilities.

What context length can it handle?

It supports up to 131072 tokens of context.

Other GGUFs of Minicpm-2B-Zero-Refusal

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →