Instructions to use second-state/MiniCPM-V-4_5-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use second-state/MiniCPM-V-4_5-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/MiniCPM-V-4_5-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use second-state/MiniCPM-V-4_5-GGUF with Ollama:
```
ollama run hf.co/second-state/MiniCPM-V-4_5-GGUF:Q4_K_M
```
Unsloth Desktop

How to use second-state/MiniCPM-V-4_5-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "second-state/MiniCPM-V-4_5-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use second-state/MiniCPM-V-4_5-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/MiniCPM-V-4_5-GGUF:Q4_K_M
```

Lemonade

How to use second-state/MiniCPM-V-4_5-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/MiniCPM-V-4_5-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM-V-4_5-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use second-state/MiniCPM-V-4_5-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default second-state/MiniCPM-V-4_5-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use second-state/MiniCPM-V-4_5-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf second-state/MiniCPM-V-4_5-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "second-state/MiniCPM-V-4_5-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

apepkuss79 commited on Aug 28, 2025

Commit

9d0a45c

verified ·

1 Parent(s): ecf7267

Update models

Browse files

Files changed (16) hide show

.gitattributes +14 -0
MiniCPM-V-4_5-Q2_K.gguf +3 -0
MiniCPM-V-4_5-Q3_K_L.gguf +3 -0
MiniCPM-V-4_5-Q3_K_M.gguf +3 -0
MiniCPM-V-4_5-Q3_K_S.gguf +3 -0
MiniCPM-V-4_5-Q4_0.gguf +3 -0
MiniCPM-V-4_5-Q4_K_M.gguf +3 -0
MiniCPM-V-4_5-Q4_K_S.gguf +3 -0
MiniCPM-V-4_5-Q5_0.gguf +3 -0
MiniCPM-V-4_5-Q5_K_M.gguf +3 -0
MiniCPM-V-4_5-Q5_K_S.gguf +3 -0
MiniCPM-V-4_5-Q6_K.gguf +3 -0
MiniCPM-V-4_5-Q8_0.gguf +3 -0
MiniCPM-V-4_5-f16.gguf +3 -0
MiniCPM-V-4_5-mmproj-f16.gguf +3 -0
config.json +58 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,17 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-f16.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM-V-4_5-mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text

MiniCPM-V-4_5-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f8493903b625b9be26b4e5359f82a82a16f923061ee0b11bbe3930364f41212f
+size 3280843968

MiniCPM-V-4_5-Q3_K_L.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5790ee2806ba2e1f67c8b04f34be07bda24fabe64b2ba9595811fcc5a9e292e2
+size 4430426944

MiniCPM-V-4_5-Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9a1c686229201d6a8afa8642785102182c8b476d6cf79486bd2f7e0574b98e
+size 4123194176

MiniCPM-V-4_5-Q3_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e462f1b1662450b643ee81e745bb32fef96ea0128e86b6b2c6c9745542073558
+size 3768644416

MiniCPM-V-4_5-Q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb2f6030aae2750c0472e3d2f6178fb84b03d336baf5a0e996c26664486d814
+size 4773680064

MiniCPM-V-4_5-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bf354f3757c9079806215f5ce86b5c7eaaca0e5e96f8369138e3482f3edef363
+size 5026714560

MiniCPM-V-4_5-Q4_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2cdcb43f3d95570841b9d0229a3daf3f98f9b8ca66debda337d5e54a690d7ba4
+size 4800943040

MiniCPM-V-4_5-Q5_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1242ae1af26cff56600223438b2ad77742b6290e2c68046e6afdd365ef5b07
+size 5719595968

MiniCPM-V-4_5-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2a9c8c2583ee94c33d63f00b87b77232761e634377100b9d31991f808f4bf9
+size 5849947072

MiniCPM-V-4_5-Q5_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9503b1ad4845e6af18b1c0f94633894283a0459c091d3c1b238aafe38f118a
+size 5719595968

MiniCPM-V-4_5-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:64909650ecc935ea97d6fb960a28335a30abb0cc5974fc6d0c3b9019b288df4c
+size 6724631616

MiniCPM-V-4_5-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:039ee4ccd0ba3b6aa2dd861ab9761c685f5c444bdaf38da8acb76dc49c77a279
+size 8707877696

MiniCPM-V-4_5-f16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:300534285bfac2187879b6e59593569df64c12463c53ebc23eb116c32a29415a
+size 16384959296

MiniCPM-V-4_5-mmproj-f16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c5833bbbb2260f90852f437bd7a3a4a1ddd58d643a270a2943ededa2ee35d3f8
+size 1095113184

config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "_name_or_path": "openbmb/MiniCPM-V-4_5",
+  "version": 4.5,
+  "architectures": [
+    "MiniCPMV"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_minicpm.MiniCPMVConfig",
+    "AutoModel": "modeling_minicpmv.MiniCPMV",
+    "AutoModelForCausalLM": "modeling_minicpmv.MiniCPMV"
+  },
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151748,
+  "batch_vision_input": true,
+  "batch_3d_resampler": true,
+  "drop_vision_last_layer": false,
+  "image_size": 448,
+  "model_type": "minicpmv",
+  "patch_size": 14,
+  "query_num": 64,
+  "slice_config": {
+    "max_slice_nums": 9,
+    "patch_size": 14,
+    "model_type": "minicpmv"
+  },
+  "slice_mode": true,
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "siglip",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  }
+}