diff --git a/cpp/src/glm/qn/mg/qn_mg.cuh b/cpp/src/glm/qn/mg/qn_mg.cuh
index 425240f87d..ef9c1db6c2 100644
--- a/cpp/src/glm/qn/mg/qn_mg.cuh
+++ b/cpp/src/glm/qn/mg/qn_mg.cuh
@@ -49,9 +49,12 @@ int qn_fit_mg(const raft::handle_t& handle,
   SimpleVec<T> w0(w0_data, loss.n_param);
 
   // Scale the regularization strength with the number of samples.
-  T l1 = 0;
+  T l1 = pams.penalty_l1;
   T l2 = pams.penalty_l2;
-  if (pams.penalty_normalized) { l2 /= n_samples; }
+  if (pams.penalty_normalized) {
+    l1 /= n_samples;
+    l2 /= n_samples;
+  }
 
   ML::GLM::detail::Tikhonov<T> reg(l2);
   ML::GLM::detail::RegularizedGLM<T, LossFunction, decltype(reg)> regularizer_obj(&loss, &reg);
diff --git a/python/cuml/tests/dask/test_dask_logistic_regression.py b/python/cuml/tests/dask/test_dask_logistic_regression.py
index f424e3ee62..2d50fdb946 100644
--- a/python/cuml/tests/dask/test_dask_logistic_regression.py
+++ b/python/cuml/tests/dask/test_dask_logistic_regression.py
@@ -73,7 +73,7 @@ def select_sk_solver(cuml_solver):
 
 
 @pytest.mark.mg
-@pytest.mark.parametrize("nrows", [1e5])
+@pytest.mark.parametrize("nrows", [1e4])
 @pytest.mark.parametrize("ncols", [20])
 @pytest.mark.parametrize("n_parts", [2, 6])
 @pytest.mark.parametrize("fit_intercept", [False, True])
@@ -273,6 +273,8 @@ def test_lbfgs(
     delayed,
     client,
     penalty="l2",
+    l1_ratio=None,
+    C=1.0,
     n_classes=2,
 ):
     tolerance = 0.005
@@ -296,20 +298,41 @@ def imp():
 
     X_df, y_df = _prep_training_data(client, X, y, n_parts)
 
-    lr = cumlLBFGS_dask(fit_intercept=fit_intercept, penalty=penalty)
+    lr = cumlLBFGS_dask(
+        solver="qn",
+        fit_intercept=fit_intercept,
+        penalty=penalty,
+        l1_ratio=l1_ratio,
+        C=C,
+        verbose=True,
+    )
     lr.fit(X_df, y_df)
     lr_coef = lr.coef_.to_numpy()
     lr_intercept = lr.intercept_.to_numpy()
 
-    sk_model = skLR(fit_intercept=fit_intercept, penalty=penalty)
+    if penalty == "l2" or penalty == "none":
+        sk_solver = "lbfgs"
+    elif penalty == "l1" or penalty == "elasticnet":
+        sk_solver = "saga"
+    else:
+        raise ValueError(f"unexpected penalty {penalty}")
+
+    sk_model = skLR(
+        solver=sk_solver,
+        fit_intercept=fit_intercept,
+        penalty=penalty,
+        l1_ratio=l1_ratio,
+        C=C,
+    )
     sk_model.fit(X, y)
     sk_coef = sk_model.coef_
     sk_intercept = sk_model.intercept_
 
-    assert len(lr_coef) == len(sk_coef)
-    for i in range(len(lr_coef)):
-        assert lr_coef[i] == pytest.approx(sk_coef[i], abs=tolerance)
-    assert lr_intercept == pytest.approx(sk_intercept, abs=tolerance)
+    if sk_solver == "lbfgs":
+        assert len(lr_coef) == len(sk_coef)
+        for i in range(len(lr_coef)):
+            assert lr_coef[i] == pytest.approx(sk_coef[i], abs=tolerance)
+        assert lr_intercept == pytest.approx(sk_intercept, abs=tolerance)
 
     # test predict
     cu_preds = lr.predict(X_df, delayed=delayed).compute().to_numpy()
@@ -329,7 +352,7 @@ def imp():
 @pytest.mark.parametrize("fit_intercept", [False, True])
 def test_noreg(fit_intercept, client):
     lr = test_lbfgs(
-        nrows=1e5,
+        nrows=1e4,
         ncols=20,
         n_parts=23,
         fit_intercept=fit_intercept,
@@ -392,7 +415,7 @@ def assert_small(X, y, n_classes):
 @pytest.mark.parametrize("n_classes", [8])
 def test_n_classes(n_parts, fit_intercept, n_classes, client):
     lr = test_lbfgs(
-        nrows=1e5,
+        nrows=1e4,
         ncols=20,
         n_parts=n_parts,
         fit_intercept=fit_intercept,
@@ -404,3 +427,57 @@ def test_n_classes(n_parts, fit_intercept, n_classes, client):
     )
 
     assert lr._num_classes == n_classes
+
+
+@pytest.mark.mg
+@pytest.mark.parametrize("fit_intercept", [False, True])
+@pytest.mark.parametrize("datatype", [np.float32])
+@pytest.mark.parametrize("delayed", [True])
+@pytest.mark.parametrize("n_classes", [2, 8])
+@pytest.mark.parametrize("C", [1.0, 10.0])
+def test_l1(fit_intercept, datatype, delayed, n_classes, C, client):
+    lr = test_lbfgs(
+        nrows=1e4,
+        ncols=20,
+        n_parts=2,
+        fit_intercept=fit_intercept,
+        datatype=datatype,
+        delayed=delayed,
+        client=client,
+        penalty="l1",
+        n_classes=n_classes,
+        C=C,
+    )
+
+    l1_strength, l2_strength = lr._get_qn_params()
+    assert l1_strength == 1.0 / lr.C
+    assert l2_strength == 0.0
+
+
+@pytest.mark.mg
+@pytest.mark.parametrize("fit_intercept", [False, True])
+@pytest.mark.parametrize("datatype", [np.float32])
+@pytest.mark.parametrize("delayed", [True])
+@pytest.mark.parametrize("n_classes", [2, 8])
+@pytest.mark.parametrize("l1_ratio", [0.2, 0.8])
+def test_elasticnet(
+    fit_intercept, datatype, delayed, n_classes, l1_ratio, client
+):
+    lr = test_lbfgs(
+        nrows=1e4,
+        ncols=20,
+        n_parts=2,
+        fit_intercept=fit_intercept,
+        datatype=datatype,
+        delayed=delayed,
+        client=client,
+        penalty="elasticnet",
+        n_classes=n_classes,
+        l1_ratio=l1_ratio,
+    )
+
+    l1_strength, l2_strength = lr._get_qn_params()
+
+    strength = 1.0 / lr.C
+    assert l1_strength == lr.l1_ratio * strength
+    assert l2_strength == (1.0 - lr.l1_ratio) * strength