LL

MiniCPM Llama3 V 2 5

LlamaGGUF by second-stateUpdated 2024-08-22
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

MiniCPM Llama3 V 2 5 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 13 quants, from 3.2 GB (Q2_K) to 16.1 GB (F16).

MiniCPM‑Llama3‑V 2.5 – 8B multimodal LLM with strong OCR and vision

MiniCPM‑Llama3‑V 2.5 is an 8.03 B parameter model built on SigLip‑400M and Llama3‑8B‑Instruct. It supports text, coding, and vision tasks, including OCR and image understanding. The model is available in multiple GGUF quantizations for llama.cpp.

Good at

  • Vision and OCR tasks
  • Coding assistance
  • Multimodal inference

Limits

  • No vision support in some quantizations
  • Requires 8 k context for estimates
  • License not specified

Best for

  • OCR extraction from images
  • Multimodal chat applications
  • Fine‑tuning with LoRA

Who it’s for. Developers and researchers needing a lightweight multimodal LLM for local inference. The model is suitable for edge deployment and custom fine‑tuning workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.8 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_05.6 GB 7.2 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
F1616.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (4.92 GB file, ~6.5 GB memory). For 12 GB VRAM, Q5_K_M (5.73 GB file, ~7.3 GB memory) is a good balance. If memory is limited to 4 GB, Q2_K (3.18 GB file, ~4.8 GB memory) is the smallest option.

What GPU do you need for MiniCPM Llama3 V 2 5?

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 Q3_K_L (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which MiniCPM Llama3 V 2 5 quant should you choose?

Q4_K_M is the usual starting point for MiniCPM Llama3 V 2 5: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 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.

If memory is tight, the smallest file is Q2_K at 3.2 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

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bysecond-state
FamilyLlama
Downloads (HF)793
Last updated2024-08-22

Frequently asked questions about MiniCPM Llama3 V 2 5

How much VRAM does MiniCPM Llama3 V 2 5 need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Llama3 V 2 5 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM Llama3 V 2 5 GGUF?

It depends on the quant: Q2_K is 3.2 GB, Q3_K_S is 3.7 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, Q4_0 is 4.7 GB, Q4_K_S is 4.7 GB and 7 more.

What context length does MiniCPM Llama3 V 2 5 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download MiniCPM Llama3 V 2 5 GGUF?

The files are on Hugging Face in the second-state/MiniCPM-Llama3-V-2_5-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 MiniCPM‑Llama3‑V 2.5 on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 6.5 GB of VRAM at 8 k context, which fits within an 8 GB budget.

Does the model support image input?

Yes, it has strong vision and OCR capabilities and can process images up to 1.8 million pixels.

Is the model open source?

The model is released under an open source license via the HuggingFace repo, but the specific license is not listed.

Other GGUFs of MiniCPM-Llama3-V-2_5

Similar models

Browse all →

More from second-state

All by second-state →

More Llama models

All Llama →

Other small models

All small models →