diff --git a/Makefile b/Makefile
index 476caac6..bcbdbe83 100644
--- a/Makefile
+++ b/Makefile
@@ -10,10 +10,6 @@ GOLLAMA_REPO?=https://github.com/go-skynet/go-llama.cpp
 GOLLAMA_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
 CPPLLAMA_VERSION?=1e6f6554aa11fa10160a5fda689e736c3c34169f
 
-# gpt4all version
-GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
-GPT4ALL_VERSION?=27a8b020c36b0df8f8b82a252d261cda47cf44b8
-
 # go-rwkv version
 RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp
 RWKV_VERSION?=661e7ae26d442f5cfebd2a0881b44e8c55949ec6
@@ -190,7 +186,6 @@ ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-fallback
 ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-ggml
 ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-grpc
 ALL_GRPC_BACKENDS+=backend-assets/util/llama-cpp-rpc-server
-ALL_GRPC_BACKENDS+=backend-assets/grpc/gpt4all
 ALL_GRPC_BACKENDS+=backend-assets/grpc/rwkv
 ALL_GRPC_BACKENDS+=backend-assets/grpc/whisper
 ALL_GRPC_BACKENDS+=backend-assets/grpc/local-store
@@ -253,18 +248,6 @@ sources/go-piper:
 sources/go-piper/libpiper_binding.a: sources/go-piper
 	$(MAKE) -C sources/go-piper libpiper_binding.a example/main piper.o
 
-## GPT4ALL
-sources/gpt4all:
-	mkdir -p sources/gpt4all
-	cd sources/gpt4all && \
-	git init && \
-	git remote add origin $(GPT4ALL_REPO) && \
-	git fetch origin && \
-	git checkout $(GPT4ALL_VERSION) && \
-	git submodule update --init --recursive --depth 1 --single-branch
-
-sources/gpt4all/gpt4all-bindings/golang/libgpt4all.a: sources/gpt4all
-	$(MAKE) -C sources/gpt4all/gpt4all-bindings/golang/ libgpt4all.a
 
 ## RWKV
 sources/go-rwkv.cpp:
@@ -318,7 +301,7 @@ sources/whisper.cpp:
 sources/whisper.cpp/libwhisper.a: sources/whisper.cpp
 	cd sources/whisper.cpp && $(MAKE) libwhisper.a libggml.a
 
-get-sources: sources/go-llama.cpp sources/gpt4all sources/go-piper sources/go-rwkv.cpp sources/whisper.cpp sources/go-bert.cpp sources/go-stable-diffusion sources/go-tiny-dream backend/cpp/llama/llama.cpp
+get-sources: sources/go-llama.cpp sources/go-piper sources/go-rwkv.cpp sources/whisper.cpp sources/go-bert.cpp sources/go-stable-diffusion sources/go-tiny-dream backend/cpp/llama/llama.cpp
 
 replace:
 	$(GOCMD) mod edit -replace github.com/donomii/go-rwkv.cpp=$(CURDIR)/sources/go-rwkv.cpp
@@ -328,7 +311,6 @@ replace:
 	$(GOCMD) mod edit -replace github.com/M0Rf30/go-tiny-dream=$(CURDIR)/sources/go-tiny-dream
 	$(GOCMD) mod edit -replace github.com/mudler/go-piper=$(CURDIR)/sources/go-piper
 	$(GOCMD) mod edit -replace github.com/mudler/go-stable-diffusion=$(CURDIR)/sources/go-stable-diffusion
-	$(GOCMD) mod edit -replace github.com/nomic-ai/gpt4all/gpt4all-bindings/golang=$(CURDIR)/sources/gpt4all/gpt4all-bindings/golang
 	$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(CURDIR)/sources/go-llama.cpp
 
 dropreplace:
@@ -339,7 +321,6 @@ dropreplace:
 	$(GOCMD) mod edit -dropreplace github.com/M0Rf30/go-tiny-dream
 	$(GOCMD) mod edit -dropreplace github.com/mudler/go-piper
 	$(GOCMD) mod edit -dropreplace github.com/mudler/go-stable-diffusion
-	$(GOCMD) mod edit -dropreplace github.com/nomic-ai/gpt4all/gpt4all-bindings/golang
 	$(GOCMD) mod edit -dropreplace github.com/go-skynet/go-llama.cpp
 
 prepare-sources: get-sources replace
@@ -349,7 +330,6 @@ prepare-sources: get-sources replace
 rebuild: ## Rebuilds the project
 	$(GOCMD) clean -cache
 	$(MAKE) -C sources/go-llama.cpp clean
-	$(MAKE) -C sources/gpt4all/gpt4all-bindings/golang/ clean
 	$(MAKE) -C sources/go-rwkv.cpp clean
 	$(MAKE) -C sources/whisper.cpp clean
 	$(MAKE) -C sources/go-stable-diffusion clean
@@ -469,8 +449,7 @@ test: prepare test-models/testmodel.ggml grpcs
 	export GO_TAGS="tts stablediffusion debug"
 	$(MAKE) prepare-test
 	HUGGINGFACE_GRPC=$(abspath ./)/backend/python/sentencetransformers/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!gpt4all && !llama && !llama-gguf"  --flake-attempts $(TEST_FLAKES) --fail-fast -v -r $(TEST_PATHS)
-	$(MAKE) test-gpt4all
+	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!llama && !llama-gguf"  --flake-attempts $(TEST_FLAKES) --fail-fast -v -r $(TEST_PATHS)
 	$(MAKE) test-llama
 	$(MAKE) test-llama-gguf
 	$(MAKE) test-tts
@@ -500,10 +479,6 @@ teardown-e2e:
 	rm -rf $(TEST_DIR) || true
 	docker stop $$(docker ps -q --filter ancestor=localai-tests)
 
-test-gpt4all: prepare-test
-	TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="gpt4all" --flake-attempts 5 -v -r $(TEST_PATHS)
-
 test-llama: prepare-test
 	TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
 	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="llama" --flake-attempts 5 -v -r $(TEST_PATHS)
@@ -730,12 +705,6 @@ backend-assets/espeak-ng-data: sources/go-piper sources/go-piper/libpiper_bindin
 	mkdir -p backend-assets/espeak-ng-data
 	@cp -rf sources/go-piper/piper-phonemize/pi/share/espeak-ng-data/. backend-assets/espeak-ng-data
 
-backend-assets/gpt4all: sources/gpt4all sources/gpt4all/gpt4all-bindings/golang/libgpt4all.a
-	mkdir -p backend-assets/gpt4all
-	@cp sources/gpt4all/gpt4all-bindings/golang/buildllm/*.so backend-assets/gpt4all/ || true
-	@cp sources/gpt4all/gpt4all-bindings/golang/buildllm/*.dylib backend-assets/gpt4all/ || true
-	@cp sources/gpt4all/gpt4all-bindings/golang/buildllm/*.dll backend-assets/gpt4all/ || true
-
 backend-assets/grpc: protogen-go replace
 	mkdir -p backend-assets/grpc
 
@@ -746,13 +715,6 @@ ifneq ($(UPX),)
 	$(UPX) backend-assets/grpc/bert-embeddings
 endif
 
-backend-assets/grpc/gpt4all: sources/gpt4all sources/gpt4all/gpt4all-bindings/golang/libgpt4all.a backend-assets/gpt4all backend-assets/grpc
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(CURDIR)/sources/gpt4all/gpt4all-bindings/golang/ LIBRARY_PATH=$(CURDIR)/sources/gpt4all/gpt4all-bindings/golang/ \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gpt4all ./backend/go/llm/gpt4all/
-ifneq ($(UPX),)
-	$(UPX) backend-assets/grpc/gpt4all
-endif
-
 backend-assets/grpc/huggingface: backend-assets/grpc
 	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/huggingface ./backend/go/llm/langchain/
 ifneq ($(UPX),)
diff --git a/backend/go/llm/gpt4all/gpt4all.go b/backend/go/llm/gpt4all/gpt4all.go
deleted file mode 100644
index 9caab48c..00000000
--- a/backend/go/llm/gpt4all/gpt4all.go
+++ /dev/null
@@ -1,62 +0,0 @@
-package main
-
-// This is a wrapper to statisfy the GRPC service interface
-// It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
-import (
-	"fmt"
-
-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	gpt4all "github.com/nomic-ai/gpt4all/gpt4all-bindings/golang"
-)
-
-type LLM struct {
-	base.SingleThread
-
-	gpt4all *gpt4all.Model
-}
-
-func (llm *LLM) Load(opts *pb.ModelOptions) error {
-	model, err := gpt4all.New(opts.ModelFile,
-		gpt4all.SetThreads(int(opts.Threads)),
-		gpt4all.SetLibrarySearchPath(opts.LibrarySearchPath))
-	llm.gpt4all = model
-	return err
-}
-
-func buildPredictOptions(opts *pb.PredictOptions) []gpt4all.PredictOption {
-	predictOptions := []gpt4all.PredictOption{
-		gpt4all.SetTemperature(float64(opts.Temperature)),
-		gpt4all.SetTopP(float64(opts.TopP)),
-		gpt4all.SetTopK(int(opts.TopK)),
-		gpt4all.SetTokens(int(opts.Tokens)),
-	}
-
-	if opts.Batch != 0 {
-		predictOptions = append(predictOptions, gpt4all.SetBatch(int(opts.Batch)))
-	}
-	return predictOptions
-}
-
-func (llm *LLM) Predict(opts *pb.PredictOptions) (string, error) {
-	return llm.gpt4all.Predict(opts.Prompt, buildPredictOptions(opts)...)
-}
-
-func (llm *LLM) PredictStream(opts *pb.PredictOptions, results chan string) error {
-	predictOptions := buildPredictOptions(opts)
-
-	go func() {
-		llm.gpt4all.SetTokenCallback(func(token string) bool {
-			results <- token
-			return true
-		})
-		_, err := llm.gpt4all.Predict(opts.Prompt, predictOptions...)
-		if err != nil {
-			fmt.Println("err: ", err)
-		}
-		llm.gpt4all.SetTokenCallback(nil)
-		close(results)
-	}()
-
-	return nil
-}
diff --git a/backend/go/llm/gpt4all/main.go b/backend/go/llm/gpt4all/main.go
deleted file mode 100644
index acf44087..00000000
--- a/backend/go/llm/gpt4all/main.go
+++ /dev/null
@@ -1,21 +0,0 @@
-package main
-
-// Note: this is started internally by LocalAI and a server is allocated for each model
-
-import (
-	"flag"
-
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
-)
-
-var (
-	addr = flag.String("addr", "localhost:50051", "the address to connect to")
-)
-
-func main() {
-	flag.Parse()
-
-	if err := grpc.StartServer(*addr, &LLM{}); err != nil {
-		panic(err)
-	}
-}
diff --git a/core/cli/worker/worker_llamacpp.go b/core/cli/worker/worker_llamacpp.go
index 5598a485..2baf51ec 100644
--- a/core/cli/worker/worker_llamacpp.go
+++ b/core/cli/worker/worker_llamacpp.go
@@ -21,7 +21,7 @@ func (r *LLamaCPP) Run(ctx *cliContext.Context) error {
 	err := assets.ExtractFiles(ctx.BackendAssets, r.BackendAssetsPath)
 	log.Debug().Msgf("Extracting backend assets files to %s", r.BackendAssetsPath)
 	if err != nil {
-		log.Warn().Msgf("Failed extracting backend assets files: %s (might be required for some backends to work properly, like gpt4all)", err)
+		log.Warn().Msgf("Failed extracting backend assets files: %s (might be required for some backends to work properly)", err)
 	}
 
 	if len(os.Args) < 4 {
diff --git a/core/cli/worker/worker_p2p.go b/core/cli/worker/worker_p2p.go
index ddb3518c..93a365cb 100644
--- a/core/cli/worker/worker_p2p.go
+++ b/core/cli/worker/worker_p2p.go
@@ -33,7 +33,7 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
 	err := assets.ExtractFiles(ctx.BackendAssets, r.BackendAssetsPath)
 	log.Debug().Msgf("Extracting backend assets files to %s", r.BackendAssetsPath)
 	if err != nil {
-		log.Warn().Msgf("Failed extracting backend assets files: %s (might be required for some backends to work properly, like gpt4all)", err)
+		log.Warn().Msgf("Failed extracting backend assets files: %s (might be required for some backends to work properly)", err)
 	}
 
 	// Check if the token is set
diff --git a/core/http/app_test.go b/core/http/app_test.go
index b21ad25a..a837e20c 100644
--- a/core/http/app_test.go
+++ b/core/http/app_test.go
@@ -563,32 +563,6 @@ var _ = Describe("API test", func() {
 				Expect(res["unit"]).To(Equal("celcius"), fmt.Sprint(res))
 				Expect(string(resp2.Choices[0].FinishReason)).To(Equal("function_call"), fmt.Sprint(resp2.Choices[0].FinishReason))
 			})
-
-			It("runs gpt4all", Label("gpt4all"), func() {
-				if runtime.GOOS != "linux" {
-					Skip("test supported only on linux")
-				}
-
-				response := postModelApplyRequest("http://127.0.0.1:9090/models/apply", modelApplyRequest{
-					URL:  "github:go-skynet/model-gallery/gpt4all-j.yaml",
-					Name: "gpt4all-j",
-				})
-
-				Expect(response["uuid"]).ToNot(BeEmpty(), fmt.Sprint(response))
-
-				uuid := response["uuid"].(string)
-
-				Eventually(func() bool {
-					response := getModelStatus("http://127.0.0.1:9090/models/jobs/" + uuid)
-					return response["processed"].(bool)
-				}, "960s", "10s").Should(Equal(true))
-
-				resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "gpt4all-j", Messages: []openai.ChatCompletionMessage{openai.ChatCompletionMessage{Role: "user", Content: "How are you?"}}})
-				Expect(err).ToNot(HaveOccurred())
-				Expect(len(resp.Choices)).To(Equal(1))
-				Expect(resp.Choices[0].Message.Content).To(ContainSubstring("well"))
-			})
-
 		})
 	})
 
@@ -792,20 +766,6 @@ var _ = Describe("API test", func() {
 			Expect(resp.Choices[0].Message.Content).ToNot(BeEmpty())
 		})
 
-		It("can generate completions from model configs", func() {
-			resp, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "gpt4all", Prompt: testPrompt})
-			Expect(err).ToNot(HaveOccurred())
-			Expect(len(resp.Choices)).To(Equal(1))
-			Expect(resp.Choices[0].Text).ToNot(BeEmpty())
-		})
-
-		It("can generate chat completions from model configs", func() {
-			resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "gpt4all-2", Messages: []openai.ChatCompletionMessage{openai.ChatCompletionMessage{Role: "user", Content: testPrompt}}})
-			Expect(err).ToNot(HaveOccurred())
-			Expect(len(resp.Choices)).To(Equal(1))
-			Expect(resp.Choices[0].Message.Content).ToNot(BeEmpty())
-		})
-
 		It("returns errors", func() {
 			_, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "foomodel", Prompt: testPrompt})
 			Expect(err).To(HaveOccurred())
diff --git a/core/http/routes/ui.go b/core/http/routes/ui.go
index 4f8afd3c..2996e9dc 100644
--- a/core/http/routes/ui.go
+++ b/core/http/routes/ui.go
@@ -267,7 +267,7 @@ func RegisterUIRoutes(app *fiber.App,
 			return c.SendString(elements.ProgressBar("100"))
 		}
 		if status.Error != nil {
-			// TODO: instead of deleting the job, we should keep it in the cache and make it dismissable
+			// TODO: instead of deleting the job, we should keep it in the cache and make it dismissable by the user
 			processingModels.DeleteUUID(jobUID)
 			return c.SendString(elements.ErrorProgress(status.Error.Error(), status.GalleryModelName))
 		}
diff --git a/core/startup/startup.go b/core/startup/startup.go
index 55f930a4..3565d196 100644
--- a/core/startup/startup.go
+++ b/core/startup/startup.go
@@ -106,7 +106,7 @@ func Startup(opts ...config.AppOption) (*config.BackendConfigLoader, *model.Mode
 		err := assets.ExtractFiles(options.BackendAssets, options.AssetsDestination)
 		log.Debug().Msgf("Extracting backend assets files to %s", options.AssetsDestination)
 		if err != nil {
-			log.Warn().Msgf("Failed extracting backend assets files: %s (might be required for some backends to work properly, like gpt4all)", err)
+			log.Warn().Msgf("Failed extracting backend assets files: %s (might be required for some backends to work properly)", err)
 		}
 	}
 
diff --git a/pkg/model/initializers.go b/pkg/model/initializers.go
index 88a08f28..11980f03 100644
--- a/pkg/model/initializers.go
+++ b/pkg/model/initializers.go
@@ -45,11 +45,6 @@ const (
 
 	LLamaCPPGRPC = "llama-cpp-grpc"
 
-	Gpt4AllLlamaBackend = "gpt4all-llama"
-	Gpt4AllMptBackend   = "gpt4all-mpt"
-	Gpt4AllJBackend     = "gpt4all-j"
-	Gpt4All             = "gpt4all"
-
 	BertEmbeddingsBackend  = "bert-embeddings"
 	RwkvBackend            = "rwkv"
 	WhisperBackend         = "whisper"
@@ -144,11 +139,10 @@ ENTRY:
 
 	// sets a priority list - first has more priority
 	priorityList := []string{
-
 		// First llama.cpp(variants) and llama-ggml to follow.
 		// We keep the fallback to prevent that if the llama.cpp variants
 		// that depends on shared libs if breaks have still a safety net.
-		LLamaCPP, LlamaGGML, Gpt4All, LLamaCPPFallback,
+		LLamaCPP, LlamaGGML, LLamaCPPFallback,
 	}
 
 	toTheEnd := []string{
@@ -434,9 +428,6 @@ func (ml *ModelLoader) BackendLoader(opts ...Option) (client grpc.Backend, err e
 	var backendToConsume string
 
 	switch backend {
-	case Gpt4AllLlamaBackend, Gpt4AllMptBackend, Gpt4AllJBackend, Gpt4All:
-		o.gRPCOptions.LibrarySearchPath = filepath.Join(o.assetDir, "backend-assets", "gpt4all")
-		backendToConsume = Gpt4All
 	case PiperBackend:
 		o.gRPCOptions.LibrarySearchPath = filepath.Join(o.assetDir, "backend-assets", "espeak-ng-data")
 		backendToConsume = PiperBackend