Ollama

What's Changed
* Quantization: `ollama create` can now quantize models when importing them using the `--quantization` or `-q` flag:


ollama create -f Modelfile -q q4_0 mymodel


> Note: `--quantization` works when importing float16 or float32 `FROM fp16.bin`

* Fixed issue where inference subprocesses wouldn't be cleaned up on shutdown.
* Ctrl+J characters will now properly add newlines in `ollama run`
* Fixed issues when running `ollama show` for vision models
* `OPTIONS` requests to the Ollama API will no longer result in errors
* Fixed issue where partially downloaded files wouldn't be cleaned up
* Added a new `done_reason` field in responses describing why generation stopped responding
* Ollama will now more accurately estimate how much memory is available on multi-GPU systems especially when running different models one after another

New Contributors
* fmaclen made their first contribution in https://github.com/ollama/ollama/pull/3884
* Renset made their first contribution in https://github.com/ollama/ollama/pull/3881
* glumia made their first contribution in https://github.com/ollama/ollama/pull/3043
* boessu made their first contribution in https://github.com/ollama/ollama/pull/4236
* gaardhus made their first contribution in https://github.com/ollama/ollama/pull/2307
* svilupp made their first contribution in https://github.com/ollama/ollama/pull/2192
* WolfTheDeveloper made their first contribution in https://github.com/ollama/ollama/pull/4300

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.34...v0.1.35-rc1


New models
* [Llava Llama 3](https://ollama.com/library/llava-llama3): A new high-performing LLaVA model fine-tuned from Llama 3 Instruct.
* [Llava Phi 3](https://ollama.com/library/llava-phi3): A new small LLaVA model fine-tuned from Phi 3.
* [StarCoder2 15B Instruct](https://ollama.com/library/starcoder2:15b-instruct): A new instruct fine-tune of the StarCoder2 model
* [CodeGemma 1.1](https://ollama.com/library/codegemma): A new release of the CodeGemma model.
* [StableLM2 12B](https://ollama.com/library/stablelm2:12b): A new 12B version of the StableLM 2 model from Stability AI
* [Moondream 2](https://ollama.com/library/moondream): Moondream 2's runtime parameters have been improved for better responses

What's Changed
* Fixed issues with LLaVa models where they would respond incorrectly after the first request
* Fixed out of memory errors when running large models such as Llama 3 70B
* Fixed various issues with Nvidia GPU discovery on Linux and Windows
* Fixed a series of Modelfile errors when running `ollama create`
* Fixed `no slots available` error that occurred when cancelling a request and then sending follow up requests
* Improved AMD GPU detection on Fedora
* Improved reliability when using the experimental `OLLAMA_NUM_PARALLEL` and `OLLAMA_MAX_LOADED` flags
* `ollama serve` will now shut down quickly, even if a model is loading

New Contributors
* drnic made their first contribution in https://github.com/ollama/ollama/pull/4116
* bernardo-bruning made their first contribution in https://github.com/ollama/ollama/pull/4111
* Drlordbasil made their first contribution in https://github.com/ollama/ollama/pull/4174
* Saif-Shines made their first contribution in https://github.com/ollama/ollama/pull/4119
* HydenLiu made their first contribution in https://github.com/ollama/ollama/pull/4194
* jl-codes made their first contribution in https://github.com/ollama/ollama/pull/3621
* Nurgo made their first contribution in https://github.com/ollama/ollama/pull/3473
* adrienbrault made their first contribution in https://github.com/ollama/ollama/pull/3129
* Darinochka made their first contribution in https://github.com/ollama/ollama/pull/3945

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.33...v0.1.34


New models:
* [Llama 3](https://ollama.com/library/llama3): a new model by Meta, and the most capable openly available LLM to date
* [Phi 3 Mini](https://ollama.com/library/phi3): a new 3.8B parameters, lightweight, state-of-the-art open model by Microsoft.
* [Moondream](https://ollama.com/library/moondream) moondream is a small vision language model designed to run efficiently on edge devices.
* [Llama 3 Gradient 1048K](https://ollama.com/library/llama3-gradient): A Llama 3 fine-tune by Gradient to support up to a 1M token context window.
* [Dolphin Llama 3](https://ollama.com/library/dolphin-llama3): The uncensored Dolphin model, trained by Eric Hartford and based on Llama 3 with a variety of instruction, conversational, and coding skills.
* [Qwen 110B](https://ollama.com/library/qwen:110b): The first Qwen model over 100B parameters in size with outstanding performance in evaluations

What's Changed
* Fixed issues where the model would not terminate, causing the API to hang.
* Fixed a series of out of memory errors on Apple Silicon Macs
* Fixed out of memory errors when running Mixtral architecture models

Experimental concurrency features

New concurrency features are coming soon to Ollama. They are available

* `OLLAMA_NUM_PARALLEL`: Handle multiple requests simultaneously for a single model
* `OLLAMA_MAX_LOADED_MODELS`: Load multiple models simultaneously

To enable these features, set the environment variables for `ollama serve`. For more info see [this guide](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-configure-ollama-server):


OLLAMA_NUM_PARALLEL=4 OLLAMA_MAX_LOADED_MODELS=4 ollama serve


New Contributors
* hmartinez82 made their first contribution in https://github.com/ollama/ollama/pull/3972
* Cephra made their first contribution in https://github.com/ollama/ollama/pull/4037
* arpitjain099 made their first contribution in https://github.com/ollama/ollama/pull/4007
* MarkWard0110 made their first contribution in https://github.com/ollama/ollama/pull/4031
* alwqx made their first contribution in https://github.com/ollama/ollama/pull/4073
* sidxt made their first contribution in https://github.com/ollama/ollama/pull/3705
* ChengenH made their first contribution in https://github.com/ollama/ollama/pull/3789
* secondtruth made their first contribution in https://github.com/ollama/ollama/pull/3503
* reid41 made their first contribution in https://github.com/ollama/ollama/pull/3612
* ericcurtin made their first contribution in https://github.com/ollama/ollama/pull/3626
* JT2M0L3Y made their first contribution in https://github.com/ollama/ollama/pull/3633
* datvodinh made their first contribution in https://github.com/ollama/ollama/pull/3655
* MapleEve made their first contribution in https://github.com/ollama/ollama/pull/3817
* swuecho made their first contribution in https://github.com/ollama/ollama/pull/3810
* brycereitano made their first contribution in https://github.com/ollama/ollama/pull/3895
* bsdnet made their first contribution in https://github.com/ollama/ollama/pull/3889
* fyxtro made their first contribution in https://github.com/ollama/ollama/pull/3855
* natalyjazzviolin made their first contribution in https://github.com/ollama/ollama/pull/3962

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.32...v0.1.33


New models
* [WizardLM 2](https://ollama.com/library/wizardlm2): State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
* `wizardlm2:8x22b`: large 8x22B model based on Mixtral 8x22B
* `wizardlm2:7b`: fast, high-performing model based on Mistral 7B
* [Snowflake Arctic Embed](https://ollama.com/library/snowflake-arctic-embed): A suite of text embedding models by Snowflake, optimized for performance.
* [Command R+](https://ollama.com/library/command-r-plus): a powerful, scalable large language model purpose-built for RAG use cases
* [DBRX](https://ollama.com/library/dbrx): A large 132B open, general-purpose LLM created by Databricks.
* [Mixtral 8x22B](https://ollama.com/library/mixtral:8x22b): the new leading Mixture of Experts (MoE) base model by Mistral AI.

What's Changed
* Ollama will now better utilize available VRAM, leading to less out-of-memory errors, as well as better GPU utilization
* When running larger models that don't fit into VRAM on macOS, Ollama will now split the model between GPU and CPU to maximize performance.
* Fixed several issues where Ollama would hang upon encountering an error
* Fix issue where using quotes in `OLLAMA_ORIGINS` would cause an error

New Contributors
* sugarforever made their first contribution in https://github.com/ollama/ollama/pull/3400
* yaroslavyaroslav made their first contribution in https://github.com/ollama/ollama/pull/3378
* Nagi-ovo made their first contribution in https://github.com/ollama/ollama/pull/3423
* ParisNeo made their first contribution in https://github.com/ollama/ollama/pull/3436
* philippgille made their first contribution in https://github.com/ollama/ollama/pull/3437
* cesto93 made their first contribution in https://github.com/ollama/ollama/pull/3461
* ThomasVitale made their first contribution in https://github.com/ollama/ollama/pull/3515
* writinwaters made their first contribution in https://github.com/ollama/ollama/pull/3539
* alexmavr made their first contribution in https://github.com/ollama/ollama/pull/3555

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.31...v0.1.32

[](https://ollama.com/blog/embedding-models)

Ollama supports embedding models. Bring your existing documents or other data, and combine it with text prompts to build RAG (retrieval augmented generation) apps using the Ollama [REST API](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-embeddings), [Python](https://github.com/ollama/ollama-python) or [Javascript](https://github.com/ollama/ollama-js) libraries.

New models
* [Qwen 1.5 32B](https://ollama.com/library/qwen:32b): A new 32B multilingual model competitive with larger models such as Mixtral
* [StarlingLM Beta](https://ollama.com/library/starling-lm:beta): A high ranking 7B model on popular benchmarks that includes a permissive Apache 2.0 license.
* [DolphinCoder StarCoder 7B](https://ollama.com/library/dolphincoder:7b): A 7B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2 7B.
* [StableLM 1.6 Chat](https://ollama.com/library/stablelm2:chat): A new version of StableLM 1.6 tuned for instruction

What's new
* Fixed issue where Ollama would hang when using certain unicode characters in the prompt such as emojis

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.30...v0.1.31

<img alt="Ollama now supports Cohere's Command R model" src="https://github.com/ollama/ollama/assets/3325447/ba99059d-2397-4fb9-84b7-d45c71518b4e" width="640" />

New models
* [Command R](https://ollama.com/library/command-r): a Large Language Model optimized for conversational interaction and long context tasks.
* [mxbai-embed-large](https://ollama.com/library/mxbai-embed-large): A new state-of-the-art large embedding model

What's Changed
* Fixed various issues with `ollama run` on Windows
* History now will work when pressing up and down arrow keys
* Right and left arrow keys will now move the cursor appropriately
* Pasting multi-line strings will now work on Windows
* Fixed issue where mounting or sharing files between Linux and Windows (e.g. via WSL or Docker) would cause errors due to having `:` in the filename.
* Improved support for AMD MI300 and MI300X Accelerators
* Improved cleanup of temporary files resulting in better space utilization

**Important change**

For filesystem compatibility, Ollama has changed model data filenames to use `-` instead of `:`. This change will be applied automatically. If downgrading to 0.1.29 or lower from 0.1.30 (on Linux or macOS only) run:


find ~/.ollama/models/blobs -type f -exec bash -c 'mv "$0" "${0//-/:}"' {} \;



New Contributors
* alitrack made their first contribution in https://github.com/ollama/ollama/pull/3111
* drazdra made their first contribution in https://github.com/ollama/ollama/pull/3338
* rapidarchitect made their first contribution in https://github.com/ollama/ollama/pull/3288
* yusufcanb made their first contribution in https://github.com/ollama/ollama/pull/3274
* jikkuatwork made their first contribution in https://github.com/ollama/ollama/pull/3178
* timothycarambat made their first contribution in https://github.com/ollama/ollama/pull/3145
* fly2tomato made their first contribution in https://github.com/ollama/ollama/pull/2946
* enoch1118 made their first contribution in https://github.com/ollama/ollama/pull/2927
* danny-avila made their first contribution in https://github.com/ollama/ollama/pull/2918
* mmo80 made their first contribution in https://github.com/ollama/ollama/pull/2881
* anaisbetts made their first contribution in https://github.com/ollama/ollama/pull/2428
* marco-souza made their first contribution in https://github.com/ollama/ollama/pull/1905
* guchenhe made their first contribution in https://github.com/ollama/ollama/pull/1944
* herval made their first contribution in https://github.com/ollama/ollama/pull/1873
* Npahlfer made their first contribution in https://github.com/ollama/ollama/pull/1623
* remy415 made their first contribution in https://github.com/ollama/ollama/pull/2279

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.1.29...v0.1.30