MI

MiniCPM4 8B

MiniCPMGGUF by mradermacherUpdated 2025-06-10
Download on Hugging Face
Parameters8.19B
Context32K
Layers32
Architectureminicpm
Smallest quant1.9 GB
Quick answer

MiniCPM4 8B needs about 5.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.9 GB (IQ1_S) to 6.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

MiniCPM4 8B – efficient 8B‑parameter LLM for end‑side devices

MiniCPM4 8B is an 8.19B‑parameter language model trained on 8T tokens. It supports a 32K context window and is released under the Apache‑2.0 license. The model is optimized for speed on edge hardware.

Good at

  • Fast decoding on low‑end GPUs
  • Long‑text handling up to 32K tokens
  • Efficient inference with small VRAM

Limits

  • No vision support
  • Requires explicit BOS token handling
  • Large VRAM needed for higher‑quality quants

Best for

  • Edge device inference
  • Chat applications on Jetson AGX Orin
  • Rapid prototyping with limited GPU memory

Who it’s for. Developers building lightweight LLM solutions for embedded systems. Researchers needing a fast, 8B‑parameter model with a large context window.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.9 GB 2.6 GB
Fits Get file →
IQ1_M2.0 GB 2.8 GB
Fits Get file →
IQ2_XXS2.3 GB 3.1 GB
Fits Get file →
IQ2_XS2.5 GB 3.3 GB
Fits Get file →
IQ2_S2.7 GB 3.4 GB
Fits Get file →
IQ2_M2.9 GB 3.6 GB
Fits Get file →
Q2_K_S2.9 GB 3.7 GB
Fits Get file →
Q2_K3.1 GB 3.9 GB
Fits Get file →
IQ3_XXS3.2 GB 4.0 GB
Fits Get file →
IQ3_XS3.5 GB 4.2 GB
Fits Get file →
Q3_K_S3.6 GB 4.4 GB
Fits Get file →
IQ3_S3.6 GB 4.4 GB
Fits Get file →
IQ3_M3.7 GB 4.5 GB
Fits Get file →
Q3_K_M4.0 GB 4.8 GB
Fits Get file →
Q3_K_L4.3 GB 5.1 GB
Fits Get file →
IQ4_XS4.4 GB 5.2 GB
Fits Get file →
IQ4_NL4.7 GB 5.5 GB
Fits Get file →
Q4_04.7 GB 5.5 GB
Fits Get file →
Q4_K_S4.7 GB 5.5 GB
Fits Get file →
Q4_K_M5.0 GB 5.7 GB
Fits Get file →
Q4_15.2 GB 5.9 GB
Fits Get file →
Q5_K_S5.7 GB 6.4 GB
Fits Get file →
Q5_K_M5.8 GB 6.6 GB
Fits Get file →
Q6_K6.7 GB 7.5 GB
Tight Get file →

For 8 GB VRAM, use IQ1_S (1.87 GB, 2.6 GB memory) or IQ1_M (2.03 GB, 2.8 GB memory). With 12 GB VRAM, IQ2_S (2.65 GB, 3.4 GB memory) or Q2_K (3.12 GB, 3.9 GB memory) are suitable. Higher‑quality quants such as Q5_K_M (5.81 GB, 6.6 GB memory) require 16 GB or more.

What GPU do you need for MiniCPM4 8B?

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 IQ3_XXS (3.2 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_1 (5.2 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 7.5 GB in use).

Which MiniCPM4 8B quant should you choose?

Q4_K_M is the usual starting point for MiniCPM4 8B: it balances file size and quality well. Here it is a 5.0 GB file.

If memory is tight, the smallest file is IQ1_S at 1.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureminicpm
Parameters8.19B
Layers32
Trained context32,768 tokens
KV cache (fp16)32 KB per token

Source

Quantized bymradermacher
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)943
Last updated2025-06-10

Frequently asked questions about MiniCPM4 8B

How much VRAM does MiniCPM4 8B need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 MiniCPM4 8B on an 8 GB GPU?

Yes, with Q6_K: the 6.7 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM4 8B GGUF?

It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.7 GB, IQ2_M is 2.9 GB and 18 more.

What context length does MiniCPM4 8B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download MiniCPM4 8B GGUF?

The files are on Hugging Face in the mradermacher/MiniCPM4-8B-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 MiniCPM4 8B 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 MiniCPM4 8B on 8 GB VRAM?

Yes, with IQ1_S or IQ1_M quants the estimated VRAM usage is 2.6 GB or 2.8 GB at 8K context.

Does MiniCPM4 8B support vision tasks?

No, the model is purely text‑based and has no vision capability.

What license applies to MiniCPM4 8B?

The model is released under the Apache‑2.0 license.

Other GGUFs of MiniCPM4-8B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More MiniCPM models

All MiniCPM →

Other small models

All small models →