diff --git a/Makefile b/Makefile
index 6f0e60ce6bbc..d2c8001ef875 100644
--- a/Makefile
+++ b/Makefile
@@ -339,7 +339,9 @@ prepare-e2e:
 	docker build --build-arg BUILD_TYPE=cublas --build-arg CUDA_MAJOR_VERSION=11 --build-arg CUDA_MINOR_VERSION=7 --build-arg FFMPEG=true -t localai-tests .
 
 run-e2e-image:
-	docker run -p 5390:8080 -e MODELS_PATH=/models -e THREADS=1 -e DEBUG=true -d --rm -v $(abspath ./tests/e2e-fixtures):/models --gpus all --name e2e-tests-$(RANDOM) localai-tests
+	cp -rfv $(abspath ./tests/e2e-fixtures)/gpu.yaml models/
+	ls -liah $(abspath ./models)
+	docker run -p 5390:8080 -e MODELS_PATH=/models -e THREADS=1 -e DEBUG=true -d --rm -v $(abspath ./models):/models --gpus all --name e2e-tests-$(RANDOM) localai-tests
 
 test-e2e:
 	@echo 'Running e2e tests'
diff --git a/tests/e2e-fixtures/gpu.yaml b/tests/e2e-fixtures/gpu.yaml
index d37c7e671ac8..7fc6e1ab638a 100644
--- a/tests/e2e-fixtures/gpu.yaml
+++ b/tests/e2e-fixtures/gpu.yaml
@@ -9,9 +9,6 @@ name: gpt-4
 mmap: true
 parameters:
   model: ggllm-test-model.bin
-  #model: llama2-22b-daydreamer-v3.ggmlv3.q6_K.bin
-  #model: wizardlm-30b-uncensored.ggmlv3.q4_K_M.bin
-  #model: upstage-llama-2-70b-instruct-v2.ggmlv3.q2_K.bin
   rope_freq_base: 10000 
   rope_freq_scale: 1
   temperature: 0.2