diff --git a/llama/llama.go b/llama/llama.go
index 7bcdddef9..f5bddbdc2 100644
--- a/llama/llama.go
+++ b/llama/llama.go
@@ -95,34 +95,24 @@ func (l *LLama) Eval(text string, opts ...PredictOption) error {
 		return fmt.Errorf("inference failed")
 	}
 
-	fmt.Println("hi 4")
-
 	C.llama_free_params(params)
 
-	fmt.Println("hi 5")
-
 	return nil
 }
 
 func (l *LLama) Predict(text string, opts ...PredictOption) (string, error) {
 	po := NewPredictOptions(opts...)
 
-	fmt.Println("predict 1")
-
 	if po.TokenCallback != nil {
 		setCallback(l.ctx, po.TokenCallback)
 	}
 
-	fmt.Println("predict 2")
-
 	input := C.CString(text)
 	if po.Tokens == 0 {
 		po.Tokens = 99999999
 	}
 	out := make([]byte, po.Tokens)
 
-	fmt.Println("predict 3")
-
 	reverseCount := len(po.StopPrompts)
 	reversePrompt := make([]*C.char, reverseCount)
 	var pass **C.char
@@ -132,8 +122,6 @@ func (l *LLama) Predict(text string, opts ...PredictOption) (string, error) {
 		pass = &reversePrompt[0]
 	}
 
-	fmt.Println("predict 4")
-
 	params := C.llama_allocate_params(input, C.int(po.Seed), C.int(po.Threads), C.int(po.Tokens), C.int(po.TopK),
 		C.float(po.TopP), C.float(po.Temperature), C.float(po.Penalty), C.int(po.Repeat),
 		C.bool(po.IgnoreEOS), C.bool(po.F16KV),
@@ -145,15 +133,12 @@ func (l *LLama) Predict(text string, opts ...PredictOption) (string, error) {
 		C.bool(po.PromptCacheRO),
 	)
 
-	fmt.Println("predict 4.5")
 	ret := C.llama_predict(params, l.ctx, (*C.char)(unsafe.Pointer(&out[0])), C.bool(po.DebugMode))
 	if ret != 0 {
 		return "", fmt.Errorf("inference failed")
 	}
 	res := C.GoString((*C.char)(unsafe.Pointer(&out[0])))
 
-	fmt.Println("predict 5")
-
 	res = strings.TrimPrefix(res, " ")
 	res = strings.TrimPrefix(res, text)
 	res = strings.TrimPrefix(res, "\n")
@@ -162,8 +147,6 @@ func (l *LLama) Predict(text string, opts ...PredictOption) (string, error) {
 		res = strings.TrimRight(res, s)
 	}
 
-	fmt.Println("predict 6")
-
 	C.llama_free_params(params)
 
 	if po.TokenCallback != nil {
diff --git a/server/routes.go b/server/routes.go
index 9490441e5..8796a37be 100644
--- a/server/routes.go
+++ b/server/routes.go
@@ -26,7 +26,6 @@ func generate(c *gin.Context) {
 	tokens := 512
 	threads := runtime.NumCPU()
 	// TODO: set prompt from template
-	fmt.Println("Generating text...")
 
 	var req api.GenerateRequest
 	if err := c.ShouldBindJSON(&req); err != nil {
@@ -34,8 +33,6 @@ func generate(c *gin.Context) {
 		return
 	}
 
-	fmt.Println(req)
-
 	l, err := llama.New(req.Model, llama.EnableF16Memory, llama.SetContext(128), llama.EnableEmbeddings, llama.SetGPULayers(gpulayers))
 	if err != nil {
 		fmt.Println("Loading the model failed:", err.Error())