diff --git a/production/helm/loki/single-binary-values.yaml b/production/helm/loki/single-binary-values.yaml
new file mode 100644
index 000000000000..c1498c052517
--- /dev/null
+++ b/production/helm/loki/single-binary-values.yaml
@@ -0,0 +1,82 @@
+---
+loki:
+  commonConfig:
+    replication_factor: 1
+  image:
+    tag: "3.0.0-rc.1-amd64-45ca2fa51"
+
+  schemaConfig:
+    configs:
+      - from: 2024-04-01
+        store: tsdb
+        object_store: s3
+        schema: v13
+        index:
+          prefix: loki_index_
+          period: 24h
+  ingester:
+    chunk_encoding: snappy
+  tracing:
+    enabled: true
+  querier:
+    # Default is 4, if you have enough memory and CPU you can increase, reduce if OOMing
+    max_concurrent: 2
+
+gateway:
+  ingress:
+    enabled: true
+    hosts:
+      - host: FIXME
+        paths:
+          - path: /
+            pathType: Prefix
+
+deploymentMode: SingleBinary
+singleBinary:
+  replicas: 1
+  resources:
+    limits:
+      cpu: 3
+      memory: 6Gi
+    requests:
+      cpu: 2
+      memory: 2Gi
+  extraEnv:
+    # Keep a little bit lower than memory limits
+    - name: GOMEMLIMIT
+      value: 5500MiB
+
+chunksCache:
+  # default is 500MB, with limited memory keep this smaller
+  writebackSizeLimit: 50MB
+
+# Enable minio for storage
+minio:
+  enabled: true
+
+# Zero out replica counts of other deployment modes
+backend:
+  replicas: 0
+read:
+  replicas: 0
+write:
+  replicas: 0
+
+ingester:
+  replicas: 0
+querier:
+  replicas: 0
+queryFrontend:
+  replicas: 0
+queryScheduler:
+  replicas: 0
+distributor:
+  replicas: 0
+compactor:
+  replicas: 0
+indexGateway:
+  replicas: 0
+bloomCompactor:
+  replicas: 0
+bloomGateway:
+  replicas: 0
diff --git a/production/helm/loki/values.yaml b/production/helm/loki/values.yaml
index 65e6d7450ac2..a9d4354e725c 100644
--- a/production/helm/loki/values.yaml
+++ b/production/helm/loki/values.yaml
@@ -178,6 +178,10 @@ loki:
     chunk_store_config:
       chunk_cache_config:
         default_validity: {{ .defaultValidity }}
+        background:
+          writeback_goroutines: {{ .writebackParallelism }}
+          writeback_buffer: {{ .writebackBuffer }}
+          writeback_size_limit: {{ .writebackSizeLimit }}
         memcached:
           batch_size: {{ .batchSize }}
           parallelism: {{ .parallelism }}
@@ -209,12 +213,19 @@ loki:
 
     query_range:
       align_queries_with_step: true
+      {{- with .Values.loki.query_range }}
+      {{- tpl (. | toYaml) $ | nindent 4 }}
+      {{- end }}
       {{- if .Values.resultsCache.enabled }}
       {{- with .Values.resultsCache }}
       cache_results: true
       results_cache:
         cache:
           default_validity: {{ .defaultValidity }}
+          background:
+            writeback_goroutines: {{ .writebackParallelism }}
+            writeback_buffer: {{ .writebackBuffer }}
+            writeback_size_limit: {{ .writebackSizeLimit }}
           memcached_client:
             consistent_hash: true
             addresses: dnssrvnoa+_memcached-client._tcp.{{ template "loki.fullname" $ }}-results-cache.{{ $.Release.Namespace }}.svc
@@ -396,6 +407,8 @@ loki:
   # --  Optional analytics configuration
   analytics: {}
   # --  Optional querier configuration
+  query_range: {}
+  # --  Optional querier configuration
   querier: {}
   # --  Optional ingester configuration
   ingester: {}
@@ -2868,6 +2881,12 @@ resultsCache:
   maxItemMemory: 5
   # -- Maximum number of connections allowed
   connectionLimit: 16384
+  # -- Max memory to use for cache write back
+  writebackSizeLimit: 500MB
+  # -- Max number of objects to use for cache write back
+  writebackBuffer: 500000
+  # -- Number of parallel threads for cache write back
+  writebackParallelism: 1
   # -- Extra init containers for results-cache pods
   initContainers: []
   # -- Annotations for the results-cache pods
@@ -2951,6 +2970,12 @@ chunksCache:
   maxItemMemory: 5
   # -- Maximum number of connections allowed
   connectionLimit: 16384
+  # -- Max memory to use for cache write back
+  writebackSizeLimit: 500MB
+  # -- Max number of objects to use for cache write back
+  writebackBuffer: 500000
+  # -- Number of parallel threads for cache write back
+  writebackParallelism: 1
   # -- Extra init containers for chunks-cache pods
   initContainers: []
   # -- Annotations for the chunks-cache pods