Skip to page content
SAVRN
Search Plan a project

Open-weight model · Image and text to text

MiniCPM-V-4.7-1B-GGUF

by Nguyen Quoc Vinh ngquocvinh/MiniCPM-V-4.7-1B-GGUF

MiniCPM-V-4.7-1B-GGUF is an open-weight model for image and text to text from Nguyen Quoc Vinh, released under Apache License 2.0. Its published files total 19.1 GB.

Community GGUF quantizations of openbmb/MiniCPM-V-4.7-1B. If this GGUF made your day easier, a coffee would make mine. I build and test these releases myself. Your coffee helps keep me going. Thank you for supporting this work.

Parameters—
Context—
Weights19.1 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Nguyen Quoc Vinh, published under apache-2.0, revision 1a5b7800f11b.

Community GGUF quantizations of openbmb/MiniCPM-V-4.7-1B. If this GGUF made your day easier, a coffee would make mine. I build and test these releases myself. Your coffee helps keep me going. Thank you for supporting this work. MiniCPM-V 4.7 1B is OpenBMB's compact multimodal model for image and video understanding. The upstream model describes single-image, multi-image, and video use, with an efficient vision encoder and on-device deployment targets. See the official model card and the upstream deployment guide. The upstream configuration declares a 262,144-token text context. The example below uses a 4,096-token context; long-context behavior has not been evaluated in this release. This…

Read Nguyen Quoc Vinh's full model card

Community GGUF quantizations of openbmb/MiniCPM-V-4.7-1B.

If this GGUF made your day easier, a coffee would make mine.
Send a coffee
I build and test these releases myself. Your coffee helps keep me going.
Thank you for supporting this work.

About MiniCPM-V 4.7

MiniCPM-V 4.7 1B is OpenBMB's compact multimodal model for image and video understanding. The upstream model describes single-image, multi-image, and video use, with an efficient vision encoder and on-device deployment targets. See the official model card and the upstream deployment guide.

The upstream configuration declares a 262,144-token text context. The example below uses a 4,096-token context; long-context behavior has not been evaluated in this release. This GGUF release keeps the vision projector in F16 and quantizes the language-model weights. The default upstream 16x visual-token compression is used.

Upstream performance versus inference time for MiniCPM-V 4.7 1B. See the original model card for its evaluation context.

These files are quantizations only; no training or fine-tuning was performed.

Quick start

With a CPU build of llama.cpp, ask a question about a local image:

./llama-mtmd-cli \
  -m MiniCPM-V-4_7-1B-Q4_K_M.gguf \
  --mmproj mmproj-model-f16.gguf \
  --chat-template-file chat_template.jinja \
  --image ./photo.jpg \
  --jinja \
  --simple-io --single-turn \
  -p 'Describe the image in one sentence.' \
  -n 128 -c 4096

Reproducibility and validation

The locked upstream BF16 checkpoint is converted to one F16 GGUF, and every quantized language-model GGUF is quantized directly from that same F16 input using a MiniCPM-V 4.7 1B-specific imatrix. No quantized GGUF is used as the source for another quantization. The projector stays in F16. The reproducibility manifest records source and runtime revisions, hashes, commands, and validation details. Artifact measurements use decimal GB (bytes / 1e9); SHA256SUMS.txt covers the published files.

Each published quantization is loaded with llama.cpp and must generate non-empty output for text and a single-image prompt. This is a compatibility smoke test, not a quality benchmark. No hold-out fidelity evaluation is published, so this card does not rank quantizations or make quality recommendations. The 2-bit, IQ, and ternary variants are experimental builds without a quality claim.

License and attribution

The upstream model is licensed under Apache 2.0. These are community GGUF quantizations, not an official OpenBMB release or endorsement.

Identity and Version

Repository
ngquocvinh/MiniCPM-V-4.7-1B-GGUF
Publisher
Nguyen Quoc Vinh
Task
Image and text to text
Modality
Image and text
Library
llama.cpp
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
1a5b7800f11be12cf1ae57288ab05d88a12fff14
First published
2026-10-14
Last updated
2026-10-15

Files and Weights

41 files, 19.1 GB in total. The weights are 32 files totalling 19.1 GB in gguf.

Weights32 files · 19.1 GB
Documentation4 files · 42.1 KB
Other4 files · 21.5 KB
Repository1 file · 3.6 KB
Every file
FileTypeSizeSHA-256
MiniCPM-V-4_7-1B-IQ1_M.ggufWeights421.5 MB 7e8de6aebfb3
MiniCPM-V-4_7-1B-IQ1_S.ggufWeights413.1 MB 6067d434f8c9
MiniCPM-V-4_7-1B-IQ2_M.ggufWeights486.9 MB c39182c45680
MiniCPM-V-4_7-1B-IQ2_S.ggufWeights475.8 MB e6d8612c9876
MiniCPM-V-4_7-1B-IQ2_XS.ggufWeights447.1 MB dda29da9cf20
MiniCPM-V-4_7-1B-IQ2_XXS.ggufWeights435.5 MB acd9c044fd7b
MiniCPM-V-4_7-1B-IQ3_M.ggufWeights562.9 MB 779cc104f967
MiniCPM-V-4_7-1B-IQ3_S.ggufWeights559.8 MB 84b7c147a23c
MiniCPM-V-4_7-1B-IQ3_XS.ggufWeights552.3 MB 93a4ea9816c3
MiniCPM-V-4_7-1B-IQ3_XXS.ggufWeights507.0 MB b19805eb0f26
MiniCPM-V-4_7-1B-IQ4_NL.ggufWeights658.7 MB 209a3caaa527
MiniCPM-V-4_7-1B-IQ4_XS.ggufWeights638.9 MB c1f96fa380cc
MiniCPM-V-4_7-1B-Q2_0.ggufWeights504.2 MB 0a66800f8c5c
MiniCPM-V-4_7-1B-Q2_K.ggufWeights505.5 MB 741bc24f3f08
MiniCPM-V-4_7-1B-Q2_K_S.ggufWeights497.8 MB cb7bad52a6b2
MiniCPM-V-4_7-1B-Q3_K_L.ggufWeights600.3 MB 85fee40ec3be
MiniCPM-V-4_7-1B-Q3_K_M.ggufWeights575.2 MB 88047431d840
MiniCPM-V-4_7-1B-Q3_K_S.ggufWeights544.3 MB 683374b0a33d
MiniCPM-V-4_7-1B-Q4_0.ggufWeights644.8 MB 8b14818af721
MiniCPM-V-4_7-1B-Q4_1.ggufWeights691.1 MB 77617c47fbdd
MiniCPM-V-4_7-1B-Q4_K_M.ggufWeights672.0 MB 665b622385ae
MiniCPM-V-4_7-1B-Q4_K_S.ggufWeights648.0 MB 268dfb61650a
MiniCPM-V-4_7-1B-Q5_0.ggufWeights738.8 MB 84d3bfbbd4d7
MiniCPM-V-4_7-1B-Q5_1.ggufWeights785.1 MB 378893235dfd
MiniCPM-V-4_7-1B-Q5_K_M.ggufWeights752.5 MB 2b2b46fec410
MiniCPM-V-4_7-1B-Q5_K_S.ggufWeights738.1 MB 7b277a05c509
MiniCPM-V-4_7-1B-Q6_K.ggufWeights837.9 MB 991260959984
MiniCPM-V-4_7-1B-Q8_0.ggufWeights1.1 GB 99debcbb5171
MiniCPM-V-4_7-1B-TQ1_0.ggufWeights469.2 MB 3861c303e052
MiniCPM-V-4_7-1B-TQ2_0.ggufWeights492.5 MB d0f04efd70d0
calibration/MiniCPM-V-4_7-1B.imatrix.ggufWeights2.3 MB c019724141f9
mmproj-model-f16.ggufWeights1.1 GB 2131eeca26bb
LICENSEDocumentation11.4 KB —
README.mdDocumentation3.7 KB —
calibration/README.mdDocumentation748 B —
reproducibility/manifest.mdDocumentation26.3 KB —
SHA256SUMS.txtOther3.8 KB —
calibration/minicpm_v_4_7_en_vi_zh_code_tool_vision.txtOther8.5 KB —
chat_template.jinjaOther7.2 KB —
reproducibility/artifact-measurements.tsvOther2.0 KB —
.gitattributesRepository3.6 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
19.1 GB
Download from Nguyen Quoc Vinh

Released by Nguyen Quoc Vinh through its official repository on Hugging Face. Read the license.

Built From

  • Derived from openbmb/MiniCPM-V-4.7-1B
  • Quantized from openbmb/MiniCPM-V-4.7-1B

Memory Requirements

PrecisionWeights in memory
As published19.1 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About MiniCPM-V-4.7-1B-GGUF

Can I use MiniCPM-V-4.7-1B-GGUF commercially?

Yes. MiniCPM-V-4.7-1B-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Non-uniform GGUF quantizations of a 512-expert MoE, produced with GSQ and RCO, with a vision projector for multimodal use. This repository provides GGUF quantizations of Qwen3.8-Flash-Next at four sizes, together with the model's vision projector (mmproj) for multimodal use. In contrast to uniform quantization, which applies a single quantization type to all weight tensors, each model here assigns a separate quantization type to every tensor. The assignment is obtained by a gradient-based search that allocates precision according to per-tensor sensitivity, subject to a total size budget. The resulting files are standard GGUF and run unmodified in llama.cpp, Ollama, and LM Studio. A…

Open weights apache-2.0 gguf
View model

Model · Image and text to text

Huihui-Qwen3.8-27B-abliterated-GGUF

Huihui.ai

This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. The newly added Huihui-Qwen3.8-27B-abliterated-Underdog-Saluki series come from ConwayResearch/Underdog-Saluki-27B-1.0 and ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF. Only layers 22 to 52 (0-based indexing) have been ablated, while the other layers remain unablated. It may come with a small disclaimer warning. Due to ConwayResearch/Underdog-Saluki-27B-1.0 not providing an imatrix file, we will attempt to perform ablation by mixing the GGUF…

Open weights apache-2.0 transformers
View model

Qwen3.8-27B uncensored by HauhauCS 0/465 Refusals. This is the Aggressive variant: direct answers, no refusal behavior, and minimal preamble on hard prompts. Every text GGUF preserves Qwen3.8's native NextN head, and this release adds HauhauCS FastMTP: a specific acceleration sidecar qualified across the complete quant lineup at maximum native context. Vision is included through the separate BF16 projector. No changes to datasets or intended capabilities. This release preserves Qwen3.8-27B's text, reasoning, agentic, image, and video capabilities while applying the HauhauCS Aggressive uncensoring profile. Pick Aggressive when you specifically want the model to get to the answer without…

Open weights apache-2.0
View model

Model · Image and text to text

Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF

Michał Piszczek

I built this quant because the ready-made FP4 file answered the wrong question. It was fast, but on my short WikiText-2 control it scored 6.4949 PPL. Plain Q40 scored 6.3798. The first higher-quality hybrid went too far the other way: good perplexity, 34.19 tok/s, and no comfortable room for 256K plus vision. This is the build that survived both gates. It is a 17.1 GB, 5.01 BPW mixed-precision GGUF of Qwen/Qwen3.8-27B. It keeps large, tolerant matrices in native NVFP4 and spends more bits on selected attention, Gated DeltaNet, and late FFN tensors. The trained MTP layer remains embedded in the same GGUF. This is not a fine-tune. I built the private calibration workload from 5,472 messages…

Open weights apache-2.0
View model

Model · Image and text to text

Qwen3.8-27B-GGUF

GGML Org

Run it in the Llama app: https://llama.app - https://huggingface.co/Qwen/Qwen3.8-27B - https://huggingface.co/incoai/Qwen3.8-27B-DFlash2 - add info

Open weights apache-2.0
View model

lm mmap --lazy-mode on -ngl 99 -c 32768 \ mmproj-Qwen3.8-Flash-Next-BF16.gguf --local-dir. llama-mtmd-cli -m IQ3S/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3S-00001-of-00002.gguf \ --mmproj mmproj-Qwen3.8-Flash-Next-BF16.gguf -lm mmap --lazy-mode on \ -md mtp-Qwen3.8-Flash-Next-Q80.gguf --draft-max 4 -lm mmap --lazy-mode on -ngl 99 -lm mmap --lazy-mode on keeps the n-gram table memory-mapped on disk: it is 28.8 GB and one row is read per token. Shard 1 wants to be resident (VRAM or RAM); shard 2 is fine on an SSD. The vision projector is a standard clip GGUF shared with the upstream tiers, 0.91 GB. Native context is 262,144 tokens and the KV cache grows with it, so start at -c 32768 and work…

Open weights apache-2.0 gguf
View model