E2B raw-Metal int4 pack — our exact int4 recipe, bi dropped, softcapped head — plus the KV-sharing assistant pack; manifest carries sizes and sha256s

.gitattributes

@@ -67,3 +67,4 @@ v4/ios-frontend/gemma4_e4b_qat_gather_raw/embed_per_layer.scale.f16 filter=lfs d
 v4/ios-frontend/gemma4_e4b_qat_gather_raw/head.f16 filter=lfs diff=lfs merge=lfs -text
 v5/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64_ple4_pe4_hsc_vfy8_msdpa_g8_wkv_stable_c131072/gemma4_e4b_qat_decode_int4lin_tbl_pf64_ple4_pe4_hsc_vfy8_msdpa_g8_wkv_stable_c131072.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
 v5/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64_ple4_pe4_hsc_vfy8_msdpa_g8_wkv_stable_c131072/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+raw-metal/gemma4_e4b_int4_rawmetal/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

raw-metal/gemma4_e4b_int4_rawmetal/gemma4_int4_pack.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f99ad880652cc363a4d4298ee65080e9e1d07424bc61c63d26db17c29c210a
-size 5171830272
+oid sha256:db5fbd607437fdaa9e5fdc6972edf38f95147ddb56e1030290b0b14dccb222e8
+size 4198751744

raw-metal/gemma4_e4b_int4_rawmetal/manifest.json

@@ -8,36 +8,60 @@
  "kernels": "CoreAIKit Gemma4Metal/g4msl-int4 (compiled at load, -DGQ=32 -DBI_FROM_SC=1, mathMode .safe)",
  "files": {
   "gemma4_int4_pack.bin": {
-   "bytes": 5171830272,
-   "sha256": "16f99ad880652cc363a4d4298ee65080e9e1d07424bc61c63d26db17c29c210a"
+   "bytes": 4198751744,
+   "sha256": "db5fbd607437fdaa9e5fdc6972edf38f95147ddb56e1030290b0b14dccb222e8"
   },
   "gemma4_int4_pack.json": {
-   "bytes": 126768,
-   "sha256": "2b1e677a8a1a852b0d78d43be32e4178b73b77be865f24c10af959b82e7f1bfb"
+   "bytes": 224280,
+   "sha256": "21e40d3db32b42007b7d45136887223fac623b134da7f6c2f69bc33a428a2274"
+  },
+  "tokenizer/tokenizer.json": {
+   "bytes": 32169626,
+   "sha256": "cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f"
+  },
+  "tokenizer/generation_config.json": {
+   "bytes": 203,
+   "sha256": "b69207f9be617e982d13cc273cce6fd88c98dda99a4bdc5e2d52ffe0a0d9f0a9"
+  },
+  "tokenizer/tokenizer_config.json": {
+   "bytes": 3729,
+   "sha256": "3ab5c7b94dc97d65ca7064496fa69b88ff875378e1cb7ee3e43070c3a8170999"
+  },
+  "tokenizer/chat_template.jinja": {
+   "bytes": 18569,
+   "sha256": "0a2c8073c878ab1da004bee933a998606537bbb62016310352c7285c3f01c5b5"
   }
  },
- "total_bytes": 5171957040,
+ "total_bytes": 4231168151,
  "requires": {
-  "bundle": "v5/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64_ple4_pe4_hsc_vfy8_msdpa_g8_wkv_stable_c131072",
-  "tables": "v4/ios-frontend/gemma4_e4b_qat_gather_raw"
+  "bundle": "v5/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64_ple4_pe4_hsc_vfy8_msdpa_g8_wkv_stable_c131072"
  },
  "provenance": {
   "hf_id": "google/gemma-4-E4B-it-qat-q4_0-unquantized",
   "ckpt": "/Users/ben/.cache/huggingface/hub/models--google--gemma-4-E4B-it-qat-q4_0-unquantized/snapshots/476025a01dbf99361c062bbeca3d6a76bb4c4566",
-  "raw_dir": "/private/tmp/claude-501/-Users-ben-git-visible/c1d5d3ab-24f6-477a-a9d7-4149dbcb74c2/scratchpad/e4b/root/visible-cx/gemma-4-E4B-CoreAI/d25ffc2433537937d612f7e751c037f037cf07e7/v4/ios-frontend/gemma4_e4b_qat_gather_raw",
+  "raw_dir": "",
   "bundle": "gemma4_e4b_qat_decode_int4lin_tbl_pf64_ple4_pe4_hsc_vfy8_msdpa_g8_wkv_stable_c131072",
   "quant": {
    "bits": 4,
    "block": 32,
    "axis": 1,
-   "qscheme": "symmetric_with_clipping",
-   "quant_min": -7,
+   "qscheme": "native_qat_grid",
+   "quant_min": -8,
    "quant_max": 7,
    "code_offset": 8,
    "scale_dtype": "f16",
    "G": 32,
    "bias": "derived",
    "bias_rule": "-8*scale, exact; kernels built with BI_FROM_SC=1"
+  },
+  "tokenizer": {
+   "source": "/Users/ben/.cache/huggingface/hub/models--google--gemma-4-E4B-it-qat-q4_0-unquantized/snapshots/476025a01dbf99361c062bbeca3d6a76bb4c4566",
+   "files": {
+    "tokenizer.json": "cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f",
+    "generation_config.json": "b69207f9be617e982d13cc273cce6fd88c98dda99a4bdc5e2d52ffe0a0d9f0a9",
+    "tokenizer_config.json": "3ab5c7b94dc97d65ca7064496fa69b88ff875378e1cb7ee3e43070c3a8170999",
+    "chat_template.jinja": "0a2c8073c878ab1da004bee933a998606537bbb62016310352c7285c3f01c5b5"
+   }
   }
  },
  "model": {
@@ -50,6 +74,12 @@
   "n_heads": 8,
   "n_kv_heads": 2,
   "heads_per_kv": 4,
+  "kv_uniform": true,
+  "n_kv_sliding": 2,
+  "hpk_sliding": 4,
+  "n_kv_full": 2,
+  "hpk_full": 4,
+  "k_eq_v": false,
   "hd_sliding": 256,
   "hd_full": 512,
   "ffn_n": 10240,
@@ -67,38 +97,50 @@
   "prod_sliding": 22,
   "prod_full": 23,
   "kv_slots": 24,
+  "ring_slots": 0,
   "final_logit_softcap": 30.0,
+  "stop_ids": [
+   1,
+   50,
+   106
+  ],
   "ple": {
    "bits": 4,
-   "granularity": "per_block",
    "block": 32,
-   "table_file": "embed_per_layer.i4",
-   "scale_file": "embed_per_layer.scale.f16",
+   "granularity": "per_block",
+   "code_offset": 8,
+   "scale_row_stride": 336,
+   "scales_per_row": 336,
+   "qscheme": "native_qat_grid",
    "table_dtype": "u8",
    "scale_dtype": "f16",
-   "table_shape": [
-    262144,
-    5376
-   ],
-   "scale_shape": [
-    262144,
-    352
-   ],
-   "scale_row_stride": 352,
-   "scales_per_row": 336,
-   "nibble_order": "element 2i -> low nibble, 2i+1 -> high; each nibble biased +8",
-   "code_offset": 8
+   "source": "embed_tokens_per_layer"
   },
+  "embed_gather": "gpu_int4",
   "head": {
-   "kind": "f16",
-   "source": "bundle sidecar head.f16",
+   "kind": "int4",
+   "qscheme": "native_qat_grid",
+   "source": "embed_tokens",
    "tied_to_embed": true,
    "shape": [
     262144,
     2560
    ]
+  },
+  "quant": {
+   "bits": 4,
+   "block": 32,
+   "axis": 1,
+   "qscheme": "native_qat_grid",
+   "quant_min": -8,
+   "quant_max": 7,
+   "code_offset": 8,
+   "scale_dtype": "f16",
+   "G": 32,
+   "bias": "derived",
+   "bias_rule": "-8*scale, exact; kernels built with BI_FROM_SC=1"
   }
  },
- "blob_sha256_streaming": "16f99ad880652cc363a4d4298ee65080e9e1d07424bc61c63d26db17c29c210a",
- "built_seconds": 38.2
+ "blob_sha256_streaming": "db5fbd607437fdaa9e5fdc6972edf38f95147ddb56e1030290b0b14dccb222e8",
+ "built_seconds": 2.4
 }

raw-metal/gemma4_e4b_int4_rawmetal/tokenizer/chat_template.jinja

@@ -0,0 +1,386 @@
+{#
+  Template: Google Gemma 4 Canonical Chat Template
+  Author: Google Gemma Engineering Team
+  Published: 2026-07-09
+  Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.
+#}
+{%- macro format_parameters(properties, required, filter_keys=false) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- set add_comma = false -%}
+        {%- if not filter_keys or key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{ key }}:{
+            {%- if value['description'] -%}
+                description:<|"|>{{ value['description'] }}<|"|>
+                {%- set add_comma = true -%}
+            {%- endif -%}
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <|"|>{{- req_item -}}<|"|>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            {%- if value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'OBJECT' -%}
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                    }
+                {%- elif value is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
+                    }
+                {%- endif -%}
+                {%- if value['required'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- set params = tool_data['function']['parameters'] -%}
+    {%- if params -%}
+        ,parameters:{
+        {%- if params['properties'] -%}
+            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+        {%- endif -%}
+        {%- if params['required'] -%}
+            required:[
+            {%- for item in params['required'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is none -%}
+        {{- 'null' -}}
+    {%- elif argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- elif argument is mapping -%}
+        {{- '{' -}}
+        {%- set ns = namespace(found_first=false) -%}
+        {%- for key, value in argument | dictsort -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {%- if escape_keys -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- else -%}
+                {{- key -}}
+            {%- endif -%}
+            :{{- format_argument(value, escape_keys=escape_keys) -}}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- elif argument is sequence -%}
+        {{- '[' -}}
+        {%- for item in argument -%}
+            {{- format_argument(item, escape_keys=escape_keys) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- argument -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+
+{%- macro format_tool_response_block(tool_name, response) -%}
+    {{- '<|tool_response>' -}}
+    {%- if response is mapping -%}
+        {{- 'response:' + tool_name + '{' -}}
+        {%- for key, value in response | dictsort -%}
+            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- else -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
+    {%- endif -%}
+    {{- '<tool_response|>' -}}
+{%- endmacro -%}
+
+{#- ===== SETUP ===== -#}
+{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
+{%- set loop_messages = messages -%}
+{%- set enable_thinking = enable_thinking | default(false) -%}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+{{- bos_token -}}
+{#- Handle System/Tool Definitions Block -#}
+{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
+    {{- '<|turn>system\n' -}}
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking -%}
+        {{- '<|think|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {{- item['text'] | trim + ' '-}}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<|tool>' -}}
+            {{- format_function_declaration(tool) | trim -}}
+            {{- '<tool|>' -}}
+        {%- endfor %}
+        {%- set ns.prev_message_type = 'tool' -%}
+    {%- endif -%}
+    {{- '<turn|>\n' -}}
+{%- endif %}
+
+{#- Pre-scan: find last user message index for reasoning guard -#}
+{%- set ns_turn = namespace(last_user_idx=-1) -%}
+{%- for i in range(loop_messages | length) -%}
+    {%- if loop_messages[i]['role'] == 'user' -%}
+        {%- set ns_turn.last_user_idx = i -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- if message['role'] != 'tool' -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+    {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
+    {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
+    {%- if not continue_same_model_turn -%}
+        {{- '<|turn>' + role + '\n' }}
+    {%- endif -%}
+
+    {#- Render reasoning/reasoning_content as thinking channel -#}
+    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
+    {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
+    {%- if thinking_text and thinking_gate -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- if message.get('tool_calls') -%}
+                {%- for tool_call in message.get('tool_calls') -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is none -%}
+                    {%- else -%}
+                        {{- raise_exception(
+                            "chat_template: tool_calls[].function.arguments must be a "
+                            "JSON object (mapping), not a string. Deserialize arguments "
+                            "before passing to the template."
+                        ) -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- set ns_tr_out = namespace(flag=false) -%}
+            {%- if message.get('tool_responses') -%}
+                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
+                {%- for tool_response in message.get('tool_responses') -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
+                    {%- set ns_tr_out.flag = true -%}
+                    {%- set ns.prev_message_type = 'tool_response' -%}
+                {%- endfor -%}
+            {%- elif message.get('tool_calls') -%}
+                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
+                {%- set ns_tool_scan = namespace(stopped=false) -%}
+                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
+                    {%- if ns_tool_scan.stopped -%}
+                    {%- elif loop_messages[k]['role'] != 'tool' -%}
+                        {%- set ns_tool_scan.stopped = true -%}
+                    {%- else -%}
+                        {%- set follow = loop_messages[k] -%}
+                        {#- Resolve tool_call_id to function name -#}
+                        {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
+                        {%- for tc in message.get('tool_calls') -%}
+                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
+                                {%- set ns_tname.name = tc['function']['name'] -%}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {#- Handle content as string or content-parts array -#}
+                        {%- set tool_body = follow.get('content') -%}
+                        {%- if tool_body is string -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- elif tool_body is sequence and tool_body is not string -%}
+                            {%- set ns_txt = namespace(s='') -%}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') == 'text' -%}
+                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
+                                {%- endif -%}
+                            {%- endfor -%}
+                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') in ['image', 'image_url'] -%}
+                                    {{- '<|image|>' -}}
+                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}
+                                    {{- '<|audio|>' -}}
+                                {%- elif part.get('type') == 'video' -%}
+                                    {{- '<|video|>' -}}
+                                {%- endif -%}
+                            {%- endfor -%}
+                        {%- else -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- endif -%}
+                        {%- set ns_tr_out.flag = true -%}
+                        {%- set ns.prev_message_type = 'tool_response' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+            {%- set captured_content -%}
+            {%- if message.get('content') is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message.get('content') is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item.get('type') == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item.get('type') in ['image', 'image_url'] -%}
+                        {{- '<|image|>' -}}
+                    {%- elif item.get('type') in ['audio', 'input_audio'] -%}
+                        {{- '<|audio|>' -}}
+                    {%- elif item.get('type') == 'video' -%}
+                        {{- '<|video|>' -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {#- Forward-scan: find next non-tool message role for continuation detection -#}
+        {%- set next_nt = namespace(role=None, found=false) -%}
+        {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
+            {%- if not next_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set next_nt.role = loop_messages[j]['role'] -%}
+                    {%- set next_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+
+        {%- set continues_into_next = (
+            role == 'model'
+            and next_nt.role == 'assistant'
+            and (not message.get('tool_calls') or ns_tr_out.flag)
+        ) -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif continues_into_next -%}
+        {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+
+    {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
+    {%- set ns.prev_non_tool_role = message['role'] -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
+        {{- '<|channel>thought\n' -}}
+    {%- endif -%}
+{%- endif -%}

raw-metal/gemma4_e4b_int4_rawmetal/tokenizer/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.6.2"
+}

raw-metal/gemma4_e4b_int4_rawmetal/tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

raw-metal/gemma4_e4b_int4_rawmetal/tokenizer/tokenizer_config.json

@@ -0,0 +1,142 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "response_template": {
+    "defaults": {
+      "role": "assistant"
+    },
+    "fields": {
+      "content": {
+        "close": [
+          "<turn|>",
+          "<|tool_response>",
+          "<eos>"
+        ],
+        "content": "text"
+      },
+      "thinking": {
+        "close": "<channel|>",
+        "content": "text",
+        "open": "<|channel>thought\n"
+      },
+      "tool_calls": {
+        "close": "<tool_call|>",
+        "content": "json",
+        "content_args": {
+          "string_delims": [
+            [
+              "<|\"|>",
+              "<|\"|>"
+            ]
+          ],
+          "unquoted_keys": true
+        },
+        "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
+        "repeats": true,
+        "transform": {
+          "function": {
+            "arguments": "{content}",
+            "name": "{name}"
+          },
+          "type": "function"
+        }
+      }
+    },
+    "start_anchor": [
+      "<|turn>model\n",
+      "<tool_response|>"
+    ]
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}