diff --git a/README.md b/README.md
index a65903d5..c5846094 100644
--- a/README.md
+++ b/README.md
@@ -45,26 +45,45 @@ Tested with:
 - [GPT4ALL-J](https://gpt4all.io/models/ggml-gpt4all-j.bin)
 - Koala
 - [cerebras-GPT with ggml](https://huggingface.co/lxe/Cerebras-GPT-2.7B-Alpaca-SP-ggml)
+- WizardLM
 - [RWKV](https://github.com/BlinkDL/RWKV-LM) models with [rwkv.cpp](https://github.com/saharNooby/rwkv.cpp)
 
-It should also be compatible with StableLM and GPTNeoX ggml models (untested)
+### Vicuna, Alpaca, LLaMa...
+
+[llama.cpp](https://github.com/ggerganov/llama.cpp) based models are compatible
+
+### GPT4ALL
 
 Note: You might need to convert older models to the new format, see [here](https://github.com/ggerganov/llama.cpp#using-gpt4all) for instance to run `gpt4all`.
 
+### GPT4ALL-J
+
+No changes required to the model.
+
 ### RWKV
 
 <details>
 
-For `rwkv` models, you need to put also the associated tokenizer along with the ggml model:
+A full example on how to run a rwkv model is in the [examples](https://github.com/go-skynet/LocalAI/tree/master/examples/rwkv).
+
+Note: rwkv models have an associated tokenizer along that needs to be provided with it:
 
 ```
-ls models
 36464540 -rw-r--r--  1 mudler mudler 1.2G May  3 10:51 rwkv_small
 36464543 -rw-r--r--  1 mudler mudler 2.4M May  3 10:51 rwkv_small.tokenizer.json
 ```
 
 </details>
 
+### Others
+
+It should also be compatible with StableLM and GPTNeoX ggml models (untested).
+
+### Hardware requirements
+
+Depending on the model you are attempting to run might need more RAM or CPU resources. Check out also [here](https://github.com/ggerganov/llama.cpp#memorydisk-requirements) for `ggml` based backends. `rwkv` is less expensive on resources.
+
+
 ## Usage
 
 > `LocalAI` comes by default as a container image. You can check out all the available images with corresponding tags [here](https://quay.io/repository/go-skynet/local-ai?tab=tags&tag=latest).
diff --git a/main.go b/main.go
index 98b7d71b..a57ac727 100644
--- a/main.go
+++ b/main.go
@@ -5,11 +5,8 @@ import (
 	"os"
 	"path/filepath"
 
-	
-
 	api "github.com/go-skynet/LocalAI/api"
 	model "github.com/go-skynet/LocalAI/pkg/model"
-	"github.com/jaypipes/ghw"
 	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
 	"github.com/urfave/cli/v2"
@@ -24,12 +21,6 @@ func main() {
 		os.Exit(1)
 	}
 
-	threads := 4
-	cpu, err := ghw.CPU()
-	if err == nil {
-		threads = int(cpu.TotalCores)
-	}
-
 	app := &cli.App{
 		Name:  "LocalAI",
 		Usage: "OpenAI compatible API for running LLaMA/GPT models locally on CPU with consumer grade hardware.",
@@ -46,7 +37,7 @@ func main() {
 				Name:        "threads",
 				DefaultText: "Number of threads used for parallel computation. Usage of the number of physical cores in the system is suggested.",
 				EnvVars:     []string{"THREADS"},
-				Value:       threads,
+				Value:       4,
 			},
 			&cli.StringFlag{
 				Name:        "models-path",