MI

MiniCPM5 1B Heretic Som

MiniCPMGGUF by mradermacherUpdated 2026-06-05
Download on Hugging Face
Parameters1.08B
Context128K
Layers24
Architecturellama
Smallest quant0.0 GB
Quick answer

MiniCPM5 1B Heretic Som needs about 1.4 GB of memory at Q4_K_M (a 0.7 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 0.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 0.8 GB.

MiniCPM5 1B Heretic Som – 1B‑parameter Llama model for local deployment

MiniCPM5 1B Heretic Som is a 1.08B‑parameter causal language model built for on‑device use. It supports coding, reasoning, and tool use. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Coding
  • Reasoning
  • Tool use

Limits

  • No vision support
  • Requires 8k context for estimates
  • License is Apache‑2.0

Best for

  • Local code generation
  • Agentic tool use
  • Resource‑constrained inference

Who it’s for. Developers and researchers who need a lightweight, open‑source LLM for local deployment. The model is suitable for desktop or edge devices with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.7 GB
Fits Get file →
IQ1_S0.4 GB 1.1 GB
Fits Get file →
IQ1_M0.4 GB 1.1 GB
Fits Get file →
IQ2_XXS0.4 GB 1.1 GB
Fits Get file →
IQ2_XS0.4 GB 1.1 GB
Fits Get file →
IQ2_S0.4 GB 1.1 GB
Fits Get file →
IQ2_M0.5 GB 1.2 GB
Fits Get file →
Q2_K_S0.5 GB 1.2 GB
Fits Get file →
Q2_K0.5 GB 1.2 GB
Fits Get file →
IQ3_XXS0.5 GB 1.2 GB
Fits Get file →
IQ3_XS0.5 GB 1.2 GB
Fits Get file →
Q3_K_S0.5 GB 1.2 GB
Fits Get file →
IQ3_S0.5 GB 1.3 GB
Fits Get file →
IQ3_M0.6 GB 1.3 GB
Fits Get file →
Q3_K_M0.6 GB 1.3 GB
Fits Get file →
Q3_K_L0.6 GB 1.3 GB
Fits Get file →
IQ4_XS0.6 GB 1.3 GB
Fits Get file →
IQ4_NL0.7 GB 1.4 GB
Fits Get file →
Q4_00.7 GB 1.4 GB
Fits Get file →
Q4_K_S0.7 GB 1.4 GB
Fits Get file →
Q4_K_M0.7 GB 1.4 GB
Fits Get file →
Q4_10.7 GB 1.4 GB
Fits Get file →
Q5_K_S0.8 GB 1.5 GB
Fits Get file →
Q5_K_M0.8 GB 1.5 GB
Fits Get file →
Q6_K0.9 GB 1.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.69 GB file, 1.4 GB memory at 8k context). If 4 GB VRAM is available, Q3_K_M (0.58 GB, 1.3 GB memory) is a good balance. For 2 GB VRAM, IQ1_S (0.35 GB, 1.1 GB memory) is recommended.

What GPU do you need for MiniCPM5 1B Heretic Som?

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 (0.9 GB file, about 1.6 GB in use).

Which MiniCPM5 1B Heretic Som quant should you choose?

Q4_K_M is the usual starting point for MiniCPM5 1B Heretic Som: it balances file size and quality well. Here it is a 0.7 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
Parameters1.08B
Layers24
Trained context131,072 tokens
KV cache (fp16)24 KB per token

Source

Quantized bymradermacher
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)579
Last updated2026-06-05

Frequently asked questions about MiniCPM5 1B Heretic Som

How much VRAM does MiniCPM5 1B Heretic Som need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.7 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 MiniCPM5 1B Heretic Som on an 8 GB GPU?

Yes, with Q6_K: the 0.9 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM5 1B Heretic Som GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.4 GB, IQ1_M is 0.4 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB and 19 more.

What context length does MiniCPM5 1B Heretic Som support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.8 GB at 32K.

Where can I download MiniCPM5 1B Heretic Som GGUF?

The files are on Hugging Face in the mradermacher/MiniCPM5-1B-heretic-som-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 1B Heretic Som 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 MiniCPM5 1B Heretic Som on 8 GB VRAM?

Yes, the Q4_K_M quant uses 1.4 GB memory at 8k context, which fits within 8 GB VRAM.

What is the smallest quant that fits in 4 GB VRAM?

The Q3_K_M quant uses 1.3 GB memory at 8k context, suitable for 4 GB VRAM.

Does this model support vision tasks?

No, the model does not include vision capabilities.

Other GGUFs of MiniCPM5-1B-heretic-som

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →