🚀 go-pugleaf

I have two Tables:

CREATE TABLE "BUY" 
(
  "CENTER_ID"	INTEGER NOT NULL,
  "ID"	INTEGER NOT NULL, 
  "FARMER_ID"	INTEGER NOT NULL,
  "FACTORY_ID"	INTEGER NOT NULL,
  "BUY_WEIGHT"	INTEGER,
 PRIMARY KEY ("CENTER_ID", "BUY_ID")
);

CREATE TABLE "FARMER" 
(
  "CENTER_ID"	INTEGER NOT NULL,
  "ID"	INTEGER NOT NULL,
  "NAME"	VARCHAR(25),
   PRIMARY KEY ("CENTER_ID", "ID")
);

I executed two queries:
1) SELECT FARMER.ID,SUM(BUY_WEIGHT) FROM FARMER INNER JOIN BUY ON FARMER.ID=BUY.FARMER_ID
  WHERE BUY.FACTORY_ID=1 AND BUY.CENTER_ID=1
  GROUP BY FARMER.ID

2)SELECT FARMER.ID,SUM(BUY_WEIGHT) FROM FARMER INNER JOIN BUY ON FARMER.ID=BUY.FARMER_ID
  WHERE BUY.FACTORY_ID=1 
  GROUP BY FARMER.ID
  HAVING BUY.CENTER_ID=1

for both the result was same but the execution of the first query longs more than 90(s) and of second query less than 1(s) !!
The plan for the first was: PLAN SORT (JOIN (FARMER NATURAL,BUY INDEX (RDB$PRIMARY4)))
and for second was: PLAN SORT (MERGE (SORT (BUY NATURAL),SORT (FARMER NATURAL)))
What is happening? Generaly what is the difference in resuls and in background between calling HAVING or WHERE for non aggregation fields?

Thanks.