Should I use the Portmanteau test or the LM test to check for autocorrelation in the residuals in a VAR model?

[titzaaa]

Hi everyone,
Should I use the Portmanteau test or the LM test to check for autocorrelation in the residuals in a VAR model?
All my variables are stationary and even playing around with the lags won't change the results.
AIC, FRE and LR all suggest 5 lags.
I am working with monthly series and I have 114 observations.
I am performing the model in Eviews and the output of the LM autocorrelation test shows the p-values for each lag. Which significance level seems appropriate?
This is what my LM test looks like:
Null hypothesis: No serial correlation at lag h
Lag LRE* stat df Prob. Rao F-stat df Prob.
1 8.410991 4 0.0776 2.133297 (4, 222.0) 0.0776
2 10.03192 4 0.0399 2.553743 (4, 222.0) 0.0399
3 1.697105 4 0.7912 0.423985 (4, 222.0) 0.7912
4 3.452674 4 0.4851 0.865985 (4, 222.0) 0.4851
5 2.066724 4 0.7235 0.516755 (4, 222.0) 0.7235
6 0.511518 4 0.9724 0.127452 (4, 222.0) 0.9724
Null hypothesis: No serial correlation at lags 1 to h
Lag LRE* stat df Prob. Rao F-stat df Prob.
1 8.410991 4 0.0776 2.133297 (4, 222.0) 0.0776
2 14.75905 8 0.0640 1.881981 (8, 218.0) 0.0640
3 15.26726 12 0.2271 1.287584 (12, 214.0) 0.2273
4 16.39810 16 0.4255 1.030257 (16, 210.0) 0.4260
5 19.28089 20 0.5036 0.966373 (20, 206.0) 0.5045
6 22.76313 24 0.5338 0.949304 (24, 202.0) 0.5351
And this is what my Portmanteau test looks like:
Lags Q-Stat Prob.* Adj Q-Stat Prob.* df
1 1.702730 --- 1.715929 --- ---
2 4.687909 --- 4.747752 --- ---
3 5.386034 --- 5.462368 --- ---
4 6.410635 --- 6.519496 --- ---
5 7.189647 --- 7.329669 --- ---
6 7.695711 0.1034 7.860219 0.0968 4
Do I have to say there is some autocorrelation on Lag 1 and 2 or is this little bit of autocorrelation okay to proceed? Is there any source I can cite to say it is okay?
Thanks a lot in advance,
Franziska