From f0078ae4766d0d570e196158f20dde309bd96124 Mon Sep 17 00:00:00 2001 From: Jeffrey Morgan Date: Sun, 7 Jun 2026 12:43:13 -0700 Subject: [PATCH] docs: update docs examples to use Gemma 4 instead of Gemma 3 (#16607) --- README.md | 10 +- docs/api/errors.mdx | 8 +- docs/api/introduction.mdx | 2 +- docs/api/streaming.mdx | 16 +-- docs/api/usage.mdx | 2 +- docs/capabilities/structured-outputs.mdx | 2 +- docs/capabilities/vision.mdx | 8 +- docs/cli.mdx | 12 +- docs/context-length.mdx | 2 +- docs/index.mdx | 2 +- docs/openapi.yaml | 154 +++++++++++++---------- docs/quickstart.mdx | 2 +- 12 files changed, 120 insertions(+), 100 deletions(-) diff --git a/README.md b/README.md index 0fc1e8ca..1e5a52d2 100644 --- a/README.md +++ b/README.md @@ -77,10 +77,10 @@ ollama launch openclaw ### Chat with a model -Run and chat with [Gemma 3](https://ollama.com/library/gemma3): +Run and chat with [Gemma 4](https://ollama.com/library/gemma4): ``` -ollama run gemma3 +ollama run gemma4 ``` See [ollama.com/library](https://ollama.com/library) for the full list. @@ -93,7 +93,7 @@ Ollama has a REST API for running and managing models. ``` curl http://localhost:11434/api/chat -d '{ - "model": "gemma3", + "model": "gemma4", "messages": [{ "role": "user", "content": "Why is the sky blue?" @@ -113,7 +113,7 @@ pip install ollama ```python from ollama import chat -response = chat(model='gemma3', messages=[ +response = chat(model='gemma4', messages=[ { 'role': 'user', 'content': 'Why is the sky blue?', @@ -132,7 +132,7 @@ npm i ollama import ollama from "ollama"; const response = await ollama.chat({ - model: "gemma3", + model: "gemma4", messages: [{ role: "user", content: "Why is the sky blue?" }], }); console.log(response.message.content); diff --git a/docs/api/errors.mdx b/docs/api/errors.mdx index 15a8809e..af6c7cb8 100644 --- a/docs/api/errors.mdx +++ b/docs/api/errors.mdx @@ -28,9 +28,9 @@ Errors are returned in the `application/json` format with the following structur If an error occurs mid-stream, the error will be returned as an object in the `application/x-ndjson` format with an `error` property. Since the response has already started, the status code of the response will not be changed. ```json -{"model":"gemma3","created_at":"2025-10-26T17:21:21.196249Z","response":" Yes","done":false} -{"model":"gemma3","created_at":"2025-10-26T17:21:21.207235Z","response":".","done":false} -{"model":"gemma3","created_at":"2025-10-26T17:21:21.219166Z","response":"I","done":false} -{"model":"gemma3","created_at":"2025-10-26T17:21:21.231094Z","response":"can","done":false} +{"model":"gemma4","created_at":"2025-10-26T17:21:21.196249Z","response":" Yes","done":false} +{"model":"gemma4","created_at":"2025-10-26T17:21:21.207235Z","response":".","done":false} +{"model":"gemma4","created_at":"2025-10-26T17:21:21.219166Z","response":"I","done":false} +{"model":"gemma4","created_at":"2025-10-26T17:21:21.231094Z","response":"can","done":false} {"error":"an error was encountered while running the model"} ``` diff --git a/docs/api/introduction.mdx b/docs/api/introduction.mdx index bc8a9ad7..596a75db 100644 --- a/docs/api/introduction.mdx +++ b/docs/api/introduction.mdx @@ -28,7 +28,7 @@ Once Ollama is running, its API is automatically available and can be accessed v ```shell curl http://localhost:11434/api/generate -d '{ - "model": "gemma3", + "model": "gemma4", "prompt": "Why is the sky blue?" }' ``` diff --git a/docs/api/streaming.mdx b/docs/api/streaming.mdx index ad77f810..89d2a255 100644 --- a/docs/api/streaming.mdx +++ b/docs/api/streaming.mdx @@ -5,13 +5,13 @@ title: Streaming Certain API endpoints stream responses by default, such as `/api/generate`. These responses are provided in the newline-delimited JSON format (i.e. the `application/x-ndjson` content type). For example: ```json -{"model":"gemma3","created_at":"2025-10-26T17:15:24.097767Z","response":"That","done":false} -{"model":"gemma3","created_at":"2025-10-26T17:15:24.109172Z","response":"'","done":false} -{"model":"gemma3","created_at":"2025-10-26T17:15:24.121485Z","response":"s","done":false} -{"model":"gemma3","created_at":"2025-10-26T17:15:24.132802Z","response":" a","done":false} -{"model":"gemma3","created_at":"2025-10-26T17:15:24.143931Z","response":" fantastic","done":false} -{"model":"gemma3","created_at":"2025-10-26T17:15:24.155176Z","response":" question","done":false} -{"model":"gemma3","created_at":"2025-10-26T17:15:24.166576Z","response":"!","done":true, "done_reason": "stop"} +{"model":"gemma4","created_at":"2025-10-26T17:15:24.097767Z","response":"That","done":false} +{"model":"gemma4","created_at":"2025-10-26T17:15:24.109172Z","response":"'","done":false} +{"model":"gemma4","created_at":"2025-10-26T17:15:24.121485Z","response":"s","done":false} +{"model":"gemma4","created_at":"2025-10-26T17:15:24.132802Z","response":" a","done":false} +{"model":"gemma4","created_at":"2025-10-26T17:15:24.143931Z","response":" fantastic","done":false} +{"model":"gemma4","created_at":"2025-10-26T17:15:24.155176Z","response":" question","done":false} +{"model":"gemma4","created_at":"2025-10-26T17:15:24.166576Z","response":"!","done":true, "done_reason": "stop"} ``` ## Disabling streaming @@ -19,7 +19,7 @@ Certain API endpoints stream responses by default, such as `/api/generate`. Thes Streaming can be disabled by providing `{"stream": false}` in the request body for any endpoint that support streaming. This will cause responses to be returned in the `application/json` format instead: ```json -{"model":"gemma3","created_at":"2025-10-26T17:15:24.166576Z","response":"That's a fantastic question!","done":true} +{"model":"gemma4","created_at":"2025-10-26T17:15:24.166576Z","response":"That's a fantastic question!","done":true} ``` ## When to use streaming vs non-streaming diff --git a/docs/api/usage.mdx b/docs/api/usage.mdx index 8317ca84..107bb0c4 100644 --- a/docs/api/usage.mdx +++ b/docs/api/usage.mdx @@ -19,7 +19,7 @@ For endpoints that return usage metrics, the response body will include the usag ```json { - "model": "gemma3", + "model": "gemma4", "created_at": "2025-10-17T23:14:07.414671Z", "response": "Hello! How can I help you today?", "done": true, diff --git a/docs/capabilities/structured-outputs.mdx b/docs/capabilities/structured-outputs.mdx index 484ba4fb..c570a12f 100644 --- a/docs/capabilities/structured-outputs.mdx +++ b/docs/capabilities/structured-outputs.mdx @@ -176,7 +176,7 @@ class ImageDescription(BaseModel): text_content: Optional[str] = None response = chat( - model='gemma3', + model='gemma4', messages=[{ 'role': 'user', 'content': 'Describe this photo and list the objects you detect.', diff --git a/docs/capabilities/vision.mdx b/docs/capabilities/vision.mdx index 81fa260e..1ecd50c4 100644 --- a/docs/capabilities/vision.mdx +++ b/docs/capabilities/vision.mdx @@ -7,7 +7,7 @@ Vision models accept images alongside text so the model can describe, classify, ## Quick start ```shell -ollama run gemma3 ./image.png whats in this image? +ollama run gemma4 ./image.png whats in this image? ``` @@ -28,7 +28,7 @@ Provide an `images` array. SDKs accept file paths, URLs or raw bytes while the R curl -X POST http://localhost:11434/api/chat \ -H "Content-Type: application/json" \ -d '{ - "model": "gemma3", + "model": "gemma4", "messages": [{ "role": "user", "content": "What is in this image?", @@ -52,7 +52,7 @@ Provide an `images` array. SDKs accept file paths, URLs or raw bytes while the R # img = Path(path).read_bytes() response = chat( - model='gemma3', + model='gemma4', messages=[ { 'role': 'user', @@ -71,7 +71,7 @@ Provide an `images` array. SDKs accept file paths, URLs or raw bytes while the R const imagePath = '/absolute/path/to/image.jpg' const response = await ollama.chat({ - model: 'gemma3', + model: 'gemma4', messages: [ { role: 'user', content: 'What is in this image?', images: [imagePath] } ], diff --git a/docs/cli.mdx b/docs/cli.mdx index 5ff2995c..8ed110ee 100644 --- a/docs/cli.mdx +++ b/docs/cli.mdx @@ -5,7 +5,7 @@ title: CLI Reference ### Run a model ``` -ollama run gemma3 +ollama run gemma4 ``` ### Launch integrations @@ -64,7 +64,7 @@ I'm a basic program that prints the famous "Hello, world!" message to the consol #### Multimodal models ``` -ollama run gemma3 "What's in this image? /Users/jmorgan/Desktop/smile.png" +ollama run gemma4 "What's in this image? /Users/jmorgan/Desktop/smile.png" ``` ### Generate embeddings @@ -82,13 +82,13 @@ echo "Hello world" | ollama run nomic-embed-text ### Download a model ``` -ollama pull gemma3 +ollama pull gemma4 ``` ### Remove a model ``` -ollama rm gemma3 +ollama rm gemma4 ``` ### List models @@ -114,7 +114,7 @@ ollama signout First, create a `Modelfile` ``` -FROM gemma3 +FROM gemma4 SYSTEM """You are a happy cat.""" ``` @@ -133,7 +133,7 @@ ollama ps ### Stop a running model ``` -ollama stop gemma3 +ollama stop gemma4 ``` ### Start Ollama diff --git a/docs/context-length.mdx b/docs/context-length.mdx index 06ae21a3..abc2133b 100644 --- a/docs/context-length.mdx +++ b/docs/context-length.mdx @@ -37,5 +37,5 @@ ollama ps ``` ``` NAME ID SIZE PROCESSOR CONTEXT UNTIL -gemma3:latest a2af6cc3eb7f 6.6 GB 100% GPU 65536 2 minutes from now +gemma4:latest c6eb396dbd59 9.6 GB 100% GPU 131072 2 minutes from now ``` diff --git a/docs/index.mdx b/docs/index.mdx index ac1c744e..10cc735d 100644 --- a/docs/index.mdx +++ b/docs/index.mdx @@ -5,7 +5,7 @@ sidebarTitle: Welcome -[Ollama](https://ollama.com) is the easiest way to get up and running with large language models such as gpt-oss, Gemma 3, DeepSeek-R1, Qwen3 and more. +[Ollama](https://ollama.com) is the easiest way to get up and running with large language models such as gpt-oss, Gemma 4, DeepSeek-R1, Qwen3 and more. diff --git a/docs/openapi.yaml b/docs/openapi.yaml index d225a476..26b122fd 100644 --- a/docs/openapi.yaml +++ b/docs/openapi.yaml @@ -794,14 +794,14 @@ paths: label: Default source: | curl http://localhost:11434/api/generate -d '{ - "model": "gemma3", + "model": "gemma4", "prompt": "Why is the sky blue?" }' - lang: bash label: Non-streaming source: | curl http://localhost:11434/api/generate -d '{ - "model": "gemma3", + "model": "gemma4", "prompt": "Why is the sky blue?", "stream": false }' @@ -809,7 +809,7 @@ paths: label: With options source: | curl http://localhost:11434/api/generate -d '{ - "model": "gemma3", + "model": "gemma4", "prompt": "Why is the sky blue?", "options": { "temperature": 0.8, @@ -821,7 +821,7 @@ paths: label: Structured outputs source: | curl http://localhost:11434/api/generate -d '{ - "model": "gemma3", + "model": "gemma4", "prompt": "What are the populations of the United States and Canada?", "stream": false, "format": { @@ -846,7 +846,7 @@ paths: label: With images source: | curl http://localhost:11434/api/generate -d '{ - "model": "gemma3", + "model": "gemma4", "prompt": "What is in this picture?", "images": ["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"] }' @@ -854,13 +854,13 @@ paths: label: Load model source: | curl http://localhost:11434/api/generate -d '{ - "model": "gemma3" + "model": "gemma4" }' - lang: bash label: Unload model source: | curl http://localhost:11434/api/generate -d '{ - "model": "gemma3", + "model": "gemma4", "keep_alive": 0 }' requestBody: @@ -870,7 +870,7 @@ paths: schema: $ref: "#/components/schemas/GenerateRequest" example: - model: gemma3 + model: gemma4 prompt: Why is the sky blue? responses: "200": @@ -880,7 +880,7 @@ paths: schema: $ref: "#/components/schemas/GenerateResponse" example: - model: "gemma3" + model: "gemma4" created_at: "2025-10-17T23:14:07.414671Z" response: "Hello! How can I help you today?" done: true @@ -906,7 +906,7 @@ paths: label: Default source: | curl http://localhost:11434/api/chat -d '{ - "model": "gemma3", + "model": "gemma4", "messages": [ { "role": "user", @@ -918,7 +918,7 @@ paths: label: Non-streaming source: | curl http://localhost:11434/api/chat -d '{ - "model": "gemma3", + "model": "gemma4", "messages": [ { "role": "user", @@ -931,7 +931,7 @@ paths: label: Structured outputs source: | curl -X POST http://localhost:11434/api/chat -H "Content-Type: application/json" -d '{ - "model": "gemma3", + "model": "gemma4", "messages": [ { "role": "user", @@ -1011,7 +1011,7 @@ paths: label: Images source: | curl http://localhost:11434/api/chat -d '{ - "model": "gemma3", + "model": "gemma4", "messages": [ { "role": "user", @@ -1036,7 +1036,7 @@ paths: schema: $ref: "#/components/schemas/ChatResponse" example: - model: "gemma3" + model: "gemma4" created_at: "2025-10-17T23:14:07.414671Z" message: role: "assistant" @@ -1148,17 +1148,17 @@ paths: $ref: "#/components/schemas/ListResponse" example: models: - - name: "gemma3" - model: "gemma3" + - name: "gemma4" + model: "gemma4" modified_at: "2025-10-03T23:34:03.409490317-07:00" - size: 3338801804 - digest: "a2af6cc3eb7fa8be8504abaf9b04e88f17a119ec3f04a3addf55f92841195f5a" + size: 9608350245 + digest: "c6eb396dbd5992bbe3f5cdb947e8bbc0ee413d7c17e2beaae69f5d569cf982eb" details: format: "gguf" - family: "gemma" + family: "gemma4" families: - - "gemma" - parameter_size: "4.3B" + - "gemma4" + parameter_size: "8.0B" quantization_level: "Q4_K_M" /api/ps: get: @@ -1181,17 +1181,17 @@ paths: $ref: "#/components/schemas/PsResponse" example: models: - - name: "gemma3" - model: "gemma3" + - name: "gemma4" + model: "gemma4" size: 6591830464 - digest: "a2af6cc3eb7fa8be8504abaf9b04e88f17a119ec3f04a3addf55f92841195f5a" + digest: "c6eb396dbd5992bbe3f5cdb947e8bbc0ee413d7c17e2beaae69f5d569cf982eb" details: parent_model: "" format: "gguf" - family: "gemma3" + family: "gemma4" families: - - "gemma3" - parameter_size: "4.3B" + - "gemma4" + parameter_size: "8.0B" quantization_level: "Q4_K_M" expires_at: "2025-10-17T16:47:07.93355-07:00" size_vram: 5333539264 @@ -1205,13 +1205,13 @@ paths: label: Default source: | curl http://localhost:11434/api/show -d '{ - "model": "gemma3" + "model": "gemma4" }' - lang: bash label: Verbose source: | curl http://localhost:11434/api/show -d '{ - "model": "gemma3", + "model": "gemma4", "verbose": true }' requestBody: @@ -1221,7 +1221,7 @@ paths: schema: $ref: "#/components/schemas/ShowRequest" example: - model: gemma3 + model: gemma4 responses: "200": description: Model information @@ -1239,44 +1239,64 @@ paths: details: parent_model: "" format: "gguf" - family: "gemma3" + family: "gemma4" families: - - "gemma3" - parameter_size: "4.3B" + - "gemma4" + parameter_size: "8.0B" quantization_level: "Q4_K_M" model_info: - gemma3.attention.head_count: 8 - gemma3.attention.head_count_kv: 4 - gemma3.attention.key_length: 256 - gemma3.attention.sliding_window: 1024 - gemma3.attention.value_length: 256 - gemma3.block_count: 34 - gemma3.context_length: 131072 - gemma3.embedding_length: 2560 - gemma3.feed_forward_length: 10240 - gemma3.mm.tokens_per_image: 256 - gemma3.vision.attention.head_count: 16 - gemma3.vision.attention.layer_norm_epsilon: 0.000001 - gemma3.vision.block_count: 27 - gemma3.vision.embedding_length: 1152 - gemma3.vision.feed_forward_length: 4304 - gemma3.vision.image_size: 896 - gemma3.vision.num_channels: 3 - gemma3.vision.patch_size: 14 - general.architecture: "gemma3" + gemma4.attention.head_count: 8 + gemma4.attention.head_count_kv: 2 + gemma4.attention.key_length: 512 + gemma4.attention.key_length_swa: 256 + gemma4.attention.layer_norm_rms_epsilon: 0.000001 + gemma4.attention.shared_kv_layers: 18 + gemma4.attention.sliding_window: 512 + gemma4.attention.value_length: 512 + gemma4.attention.value_length_swa: 256 + gemma4.audio.attention.head_count: 8 + gemma4.audio.attention.layer_norm_epsilon: 0.000001 + gemma4.audio.block_count: 12 + gemma4.audio.conv_kernel_size: 5 + gemma4.audio.embedding_length: 1024 + gemma4.audio.feed_forward_length: 4096 + gemma4.block_count: 42 + gemma4.context_length: 131072 + gemma4.embedding_length: 2560 + gemma4.embedding_length_per_layer_input: 256 + gemma4.feed_forward_length: 10240 + gemma4.final_logit_softcapping: 30 + gemma4.rope.dimension_count: 512 + gemma4.rope.dimension_count_swa: 256 + gemma4.rope.freq_base: 1000000 + gemma4.rope.freq_base_swa: 10000 + gemma4.vision.attention.head_count: 12 + gemma4.vision.attention.layer_norm_epsilon: 0.000001 + gemma4.vision.block_count: 16 + gemma4.vision.embedding_length: 768 + gemma4.vision.feed_forward_length: 3072 + gemma4.vision.num_channels: 3 + gemma4.vision.patch_size: 16 + gemma4.vision.projector.scale_factor: 3 + general.architecture: "gemma4" general.file_type: 15 - general.parameter_count: 4299915632 general.quantization_version: 2 - tokenizer.ggml.add_bos_token: true + tokenizer.ggml.add_bos_token: false tokenizer.ggml.add_eos_token: false + tokenizer.ggml.add_mask_token: false tokenizer.ggml.add_padding_token: false tokenizer.ggml.add_unknown_token: false tokenizer.ggml.bos_token_id: 2 tokenizer.ggml.eos_token_id: 1 + tokenizer.ggml.eos_token_ids: + - 1 + - 106 + - 50 + tokenizer.ggml.mask_token_id: 4 tokenizer.ggml.merges: null tokenizer.ggml.model: "llama" tokenizer.ggml.padding_token_id: 0 - tokenizer.ggml.pre: "default" + tokenizer.ggml.pre: "gemma4" tokenizer.ggml.scores: null tokenizer.ggml.token_type: null tokenizer.ggml.tokens: null @@ -1292,7 +1312,7 @@ paths: label: Default source: | curl http://localhost:11434/api/create -d '{ - "from": "gemma3", + "from": "gemma4", "model": "alpaca", "system": "You are Alpaca, a helpful AI assistant. You only answer with Emojis." }' @@ -1301,7 +1321,7 @@ paths: source: | curl http://localhost:11434/api/create -d '{ "model": "ollama", - "from": "gemma3", + "from": "gemma4", "system": "You are Ollama the llama." }' - lang: bash @@ -1320,7 +1340,7 @@ paths: $ref: "#/components/schemas/CreateRequest" example: model: mario - from: gemma3 + from: gemma4 system: "You are Mario from Super Mario Bros." responses: "200": @@ -1347,8 +1367,8 @@ paths: label: Copy a model to a new name source: | curl http://localhost:11434/api/copy -d '{ - "source": "gemma3", - "destination": "gemma3-backup" + "source": "gemma4", + "destination": "gemma4-backup" }' requestBody: required: true @@ -1357,8 +1377,8 @@ paths: schema: $ref: "#/components/schemas/CopyRequest" example: - source: gemma3 - destination: gemma3-backup + source: gemma4 + destination: gemma4-backup responses: "200": description: Model successfully copied @@ -1373,13 +1393,13 @@ paths: label: Default source: | curl http://localhost:11434/api/pull -d '{ - "model": "gemma3" + "model": "gemma4" }' - lang: bash label: Non-streaming source: | curl http://localhost:11434/api/pull -d '{ - "model": "gemma3", + "model": "gemma4", "stream": false }' requestBody: @@ -1389,7 +1409,7 @@ paths: schema: $ref: "#/components/schemas/PullRequest" example: - model: gemma3 + model: gemma4 responses: "200": description: Pull status updates. @@ -1457,7 +1477,7 @@ paths: label: Delete model source: | curl -X DELETE http://localhost:11434/api/delete -d '{ - "model": "gemma3" + "model": "gemma4" }' requestBody: required: true @@ -1466,7 +1486,7 @@ paths: schema: $ref: "#/components/schemas/DeleteRequest" example: - model: gemma3 + model: gemma4 responses: "200": description: Model successfully deleted diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx index 62f2f99b..6f11a677 100644 --- a/docs/quickstart.mdx +++ b/docs/quickstart.mdx @@ -59,7 +59,7 @@ Use the [API](/api) to integrate Ollama into your applications: ```sh curl http://localhost:11434/api/chat -d '{ - "model": "gemma3", + "model": "gemma4", "messages": [{ "role": "user", "content": "Hello!" }] }' ```