Hugging Face's logo

Kecven
/
Qwen3.8-27B-MTPLX-Q4

MLX
Safetensors
qwen3_5
mtplx
qwen
qwen3.8
speculative-decoding
mtp
quantized
4-bit precision
Model card Files
xet
 Community
Kecven commited on
Commit
32ff0b1
·
verified ·
1 Parent(s): b822e5e

Publish MTPLX forged model

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. README.md +7 -0
  3. chat_template.jinja +170 -0
  4. config.json +160 -0
  5. generation_config.json +12 -0
  6. model-00001-of-00003.safetensors +3 -0
  7. model-00002-of-00003.safetensors +3 -0
  8. model-00003-of-00003.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. mtp.safetensors +3 -0
  11. mtplx_runtime.json +139 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +33 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ pipeline_tag: text-generation
4
+ tags:
5
+ - mlx
6
+ library_name: mlx
7
+ ---
chat_template.jinja ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- set reasoning_instructions = '' %}
46
+ {%- if enable_thinking is undefined or enable_thinking is true %}
47
+ {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
48
+ {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
49
+ {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
50
+ {%- endif %}
51
+ {%- if resolved_reasoning_effort == 'xhigh' %}
52
+ {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
53
+ {%- elif resolved_reasoning_effort == 'low' %}
54
+ {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
55
+ {%- endif %}
56
+ {%- endif %}
57
+ {%- if tools and tools is iterable and tools is not mapping %}
58
+ {{- '<|im_start|>system\n' }}
59
+ {%- if reasoning_instructions %}
60
+ {{- reasoning_instructions + '\n\n' }}
61
+ {%- endif %}
62
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
63
+ {%- for tool in tools %}
64
+ {{- "\n" }}
65
+ {{- tool | tojson }}
66
+ {%- endfor %}
67
+ {{- "\n</tools>" }}
68
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
69
+ {%- if messages[0].role == 'system' %}
70
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
71
+ {%- if content %}
72
+ {{- '\n\n' + content }}
73
+ {%- endif %}
74
+ {%- endif %}
75
+ {{- '<|im_end|>\n' }}
76
+ {%- else %}
77
+ {%- if messages[0].role == 'system' %}
78
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
79
+ {%- if content %}
80
+ {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }}
81
+ {%- elif reasoning_instructions %}
82
+ {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
83
+ {%- endif %}
84
+ {%- elif reasoning_instructions %}
85
+ {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
86
+ {%- endif %}
87
+ {%- endif %}
88
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
89
+ {%- for message in messages[::-1] %}
90
+ {%- set index = (messages|length - 1) - loop.index0 %}
91
+ {%- if ns.multi_step_tool and message.role == "user" %}
92
+ {%- set content = render_content(message.content, false)|trim %}
93
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
94
+ {%- set ns.multi_step_tool = false %}
95
+ {%- set ns.last_query_index = index %}
96
+ {%- endif %}
97
+ {%- endif %}
98
+ {%- endfor %}
99
+ {%- if ns.multi_step_tool %}
100
+ {{- raise_exception('No user query found in messages.') }}
101
+ {%- endif %}
102
+ {%- for message in messages %}
103
+ {%- set content = render_content(message.content, true)|trim %}
104
+ {%- if message.role == "system" %}
105
+ {%- if not loop.first %}
106
+ {{- raise_exception('System message must be at the beginning.') }}
107
+ {%- endif %}
108
+ {%- elif message.role == "user" %}
109
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
110
+ {%- elif message.role == "assistant" %}
111
+ {%- set reasoning_content = '' %}
112
+ {%- if message.reasoning_content is string %}
113
+ {%- set reasoning_content = message.reasoning_content %}
114
+ {%- endif %}
115
+ {%- set reasoning_content = reasoning_content|trim %}
116
+ {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
117
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
118
+ {%- else %}
119
+ {{- '<|im_start|>' + message.role + '\n' + content }}
120
+ {%- endif %}
121
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
122
+ {%- for tool_call in message.tool_calls %}
123
+ {%- if tool_call.function is defined %}
124
+ {%- set tool_call = tool_call.function %}
125
+ {%- endif %}
126
+ {%- if loop.first %}
127
+ {%- if content|trim %}
128
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
129
+ {%- else %}
130
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
131
+ {%- endif %}
132
+ {%- else %}
133
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
134
+ {%- endif %}
135
+ {%- if tool_call.arguments is defined and tool_call.arguments != '' %}
136
+ {%- for args_name, args_value in tool_call.arguments|items %}
137
+ {{- '<parameter=' + args_name + '>\n' }}
138
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
139
+ {{- args_value }}
140
+ {{- '\n</parameter>\n' }}
141
+ {%- endfor %}
142
+ {%- endif %}
143
+ {{- '</function>\n</tool_call>' }}
144
+ {%- endfor %}
145
+ {%- endif %}
146
+ {{- '<|im_end|>\n' }}
147
+ {%- elif message.role == "tool" %}
148
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
149
+ {{- '<|im_start|>user' }}
150
+ {%- endif %}
151
+ {{- '\n<tool_response>\n' }}
152
+ {{- content }}
153
+ {{- '\n</tool_response>' }}
154
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
155
+ {{- '<|im_end|>\n' }}
156
+ {%- elif loop.last %}
157
+ {{- '<|im_end|>\n' }}
158
+ {%- endif %}
159
+ {%- else %}
160
+ {{- raise_exception('Unexpected message role.') }}
161
+ {%- endif %}
162
+ {%- endfor %}
163
+ {%- if add_generation_prompt %}
164
+ {{- '<|im_start|>assistant\n' }}
165
+ {%- if enable_thinking is defined and enable_thinking is false %}
166
+ {{- '<think>\n\n</think>\n\n' }}
167
+ {%- else %}
168
+ {{- '<think>\n' }}
169
+ {%- endif %}
170
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "eos_token_id": [
6
+ 248046,
7
+ 248044
8
+ ],
9
+ "image_token_id": 248056,
10
+ "language_model_only": false,
11
+ "mlx_lm_extra_tensors": {
12
+ "mtp_file": "mtp.safetensors"
13
+ },
14
+ "model_type": "qwen3_5",
15
+ "mtplx_mtp_contract": {
16
+ "base_hidden_variant": "post_norm",
17
+ "concat_order": "embedding_hidden",
18
+ "hidden_variant": "post_norm",
19
+ "mtp_position_mode": "local",
20
+ "mtp_quant_group_size": 64,
21
+ "mtp_quant_mode": "affine"
22
+ },
23
+ "mtplx_mtp_payload_audit": {
24
+ "mtp_file": "/Users/andrei/.mtplx/models/Qwen3.8-27B-MTPLX-Q4/mtp.safetensors",
25
+ "nonzero_payload_tensor_count": 8,
26
+ "passed": true,
27
+ "payload_tensor_count": 8,
28
+ "problems": [],
29
+ "scale_tensor_count": 0,
30
+ "tensor_count": 15,
31
+ "zero_payload_sample": [],
32
+ "zero_scale_sample": []
33
+ },
34
+ "quantization": {
35
+ "bits": 4,
36
+ "group_size": 64,
37
+ "mode": "affine"
38
+ },
39
+ "quantization_config": {
40
+ "bits": 4,
41
+ "group_size": 64,
42
+ "mode": "affine"
43
+ },
44
+ "text_config": {
45
+ "attention_bias": false,
46
+ "attention_dropout": 0.0,
47
+ "attn_output_gate": true,
48
+ "bos_token_id": 248044,
49
+ "dtype": "bfloat16",
50
+ "eos_token_id": 248044,
51
+ "full_attention_interval": 4,
52
+ "head_dim": 256,
53
+ "hidden_act": "silu",
54
+ "hidden_size": 5120,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 17408,
57
+ "layer_types": [
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "full_attention",
66
+ "linear_attention",
67
+ "linear_attention",
68
+ "linear_attention",
69
+ "full_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "linear_attention",
73
+ "full_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "linear_attention",
77
+ "full_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "linear_attention",
81
+ "full_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "linear_attention",
85
+ "full_attention",
86
+ "linear_attention",
87
+ "linear_attention",
88
+ "linear_attention",
89
+ "full_attention",
90
+ "linear_attention",
91
+ "linear_attention",
92
+ "linear_attention",
93
+ "full_attention",
94
+ "linear_attention",
95
+ "linear_attention",
96
+ "linear_attention",
97
+ "full_attention",
98
+ "linear_attention",
99
+ "linear_attention",
100
+ "linear_attention",
101
+ "full_attention",
102
+ "linear_attention",
103
+ "linear_attention",
104
+ "linear_attention",
105
+ "full_attention",
106
+ "linear_attention",
107
+ "linear_attention",
108
+ "linear_attention",
109
+ "full_attention",
110
+ "linear_attention",
111
+ "linear_attention",
112
+ "linear_attention",
113
+ "full_attention",
114
+ "linear_attention",
115
+ "linear_attention",
116
+ "linear_attention",
117
+ "full_attention",
118
+ "linear_attention",
119
+ "linear_attention",
120
+ "linear_attention",
121
+ "full_attention"
122
+ ],
123
+ "linear_conv_kernel_dim": 4,
124
+ "linear_key_head_dim": 128,
125
+ "linear_num_key_heads": 16,
126
+ "linear_num_value_heads": 48,
127
+ "linear_value_head_dim": 128,
128
+ "mamba_ssm_dtype": "float32",
129
+ "max_position_embeddings": 262144,
130
+ "model_type": "qwen3_5_text",
131
+ "mtp_num_hidden_layers": 1,
132
+ "mtp_use_dedicated_embeddings": false,
133
+ "num_attention_heads": 24,
134
+ "num_hidden_layers": 64,
135
+ "num_key_value_heads": 4,
136
+ "output_gate_type": "swish",
137
+ "pad_token_id": null,
138
+ "partial_rotary_factor": 0.25,
139
+ "rms_norm_eps": 1e-06,
140
+ "rope_parameters": {
141
+ "mrope_interleaved": true,
142
+ "mrope_section": [
143
+ 11,
144
+ 11,
145
+ 10
146
+ ],
147
+ "partial_rotary_factor": 0.25,
148
+ "rope_theta": 10000000,
149
+ "type": "default"
150
+ },
151
+ "tie_word_embeddings": false,
152
+ "use_cache": true,
153
+ "vocab_size": 248320
154
+ },
155
+ "tie_word_embeddings": false,
156
+ "transformers_version": "5.8.0.dev0",
157
+ "video_token_id": 248057,
158
+ "vision_end_token_id": 248054,
159
+ "vision_start_token_id": 248053
160
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95
12
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075eac5fbba3951bc4870c1ac65d684c32e0abb24284201bd27f49df56735963
3
+ size 5328325648
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c99c446987a432beb1f6ef7d6fde6db02682f1ebe1a913760953140e0fa4e47
3
+ size 5354185130
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e267246064a1e635077dd05e22181f5eda44a1fa8a67dcf46c903f858bbe35b
3
+ size 4450532735
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
mtp.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4468f39621de68a19ffd0bcb2e2e2f352205def7436a625b3427e3752866c287
3
+ size 849400403
mtplx_runtime.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "arch_id": "qwen3-next-mtp",
3
+ "artifact_role": "forge-local",
4
+ "base_trunk": "Qwen/Qwen3.8-27B",
5
+ "exactness_baseline": {},
6
+ "forge_provenance": {
7
+ "forge_inputs": {
8
+ "mtp_source_path": "/Users/andrei/.mtplx/models/Qwen--Qwen3.8-27B",
9
+ "trunk_path": "/Users/andrei/.mtplx/models/Qwen3.8-27B-MTPLX-Q4"
10
+ },
11
+ "forge_recipe": {
12
+ "body_bits": 4,
13
+ "body_dtype": "auto",
14
+ "body_group_size": 64,
15
+ "body_mode": "affine",
16
+ "mtp_policy": "keep_bf16"
17
+ },
18
+ "forged_at": "2026-08-14T19:18:42-04:00",
19
+ "forged_locally": true,
20
+ "mtp_contract": {
21
+ "base_hidden_variant": "post_norm",
22
+ "concat_order": "embedding_hidden",
23
+ "hidden_variant": "post_norm",
24
+ "mtp_position_mode": "local",
25
+ "mtp_quant_group_size": 64,
26
+ "mtp_quant_mode": "affine"
27
+ },
28
+ "mtplx_version": "2.3.0",
29
+ "published_to_hf": null,
30
+ "source_format": "bf16_native",
31
+ "source_repo": "Qwen/Qwen3.8-27B",
32
+ "source_sha": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0"
33
+ },
34
+ "mtp_contract": {
35
+ "base_hidden_variant": "post_norm",
36
+ "concat_order": "embedding_hidden",
37
+ "hidden_variant": "post_norm",
38
+ "mtp_position_mode": "local",
39
+ "mtp_quant_group_size": 64,
40
+ "mtp_quant_mode": "affine"
41
+ },
42
+ "mtp_depth_max": 3,
43
+ "mtp_sidecar": "bf16",
44
+ "mtplx_version": "2.3.0",
45
+ "recommended_profile": "sustained",
46
+ "sampler": {
47
+ "temperature": 0.6,
48
+ "top_k": 20,
49
+ "top_p": 0.95
50
+ },
51
+ "speed_evidence": {
52
+ "acceptance_by_depth": [
53
+ 0.9589552238805971,
54
+ 0.8955223880597015,
55
+ 0.8171641791044776
56
+ ],
57
+ "acceptance_collapsed": [],
58
+ "depth": 3,
59
+ "failure_reasons": [],
60
+ "forge_verify_rows": [
61
+ {
62
+ "acceptance_by_position": [],
63
+ "depth": 0,
64
+ "finish_reasons": {
65
+ "stop": 1
66
+ },
67
+ "hit_token_budget": false,
68
+ "hit_token_budget_count": 0,
69
+ "multiplier_vs_ar": 1.0,
70
+ "quality_passed": true,
71
+ "tok_s": 15.73748444880254,
72
+ "verify_time_s": 96.53509454200002
73
+ },
74
+ {
75
+ "acceptance_by_position": [
76
+ 0.9694835680751174
77
+ ],
78
+ "depth": 1,
79
+ "finish_reasons": {
80
+ "stop": 1
81
+ },
82
+ "hit_token_budget": false,
83
+ "hit_token_budget_count": 0,
84
+ "multiplier_vs_ar": 1.768037970129636,
85
+ "quality_passed": true,
86
+ "tok_s": 27.824470059807556,
87
+ "verify_time_s": 28.047978162999698
88
+ },
89
+ {
90
+ "acceptance_by_position": [
91
+ 0.9612756264236902,
92
+ 0.9066059225512528
93
+ ],
94
+ "depth": 2,
95
+ "finish_reasons": {
96
+ "stop": 1
97
+ },
98
+ "hit_token_budget": false,
99
+ "hit_token_budget_count": 0,
100
+ "multiplier_vs_ar": 2.321357231944935,
101
+ "quality_passed": true,
102
+ "tok_s": 36.53232333784873,
103
+ "verify_time_s": 29.569255522001527
104
+ },
105
+ {
106
+ "acceptance_by_position": [
107
+ 0.9589552238805971,
108
+ 0.8955223880597015,
109
+ 0.8171641791044776
110
+ ],
111
+ "depth": 3,
112
+ "finish_reasons": {
113
+ "stop": 1
114
+ },
115
+ "hit_token_budget": false,
116
+ "hit_token_budget_count": 0,
117
+ "multiplier_vs_ar": 2.8173872540518663,
118
+ "quality_passed": true,
119
+ "tok_s": 44.33858809689574,
120
+ "verify_time_s": 20.3628517039989
121
+ }
122
+ ],
123
+ "greedy_diagnostic": {
124
+ "tok_s": 15.73748444880254
125
+ },
126
+ "quality_rejected": [],
127
+ "tok_s": [
128
+ 44.33858809689574
129
+ ],
130
+ "verdict": "mtp_depth_wins"
131
+ },
132
+ "verified_on": {
133
+ "hardware": "macOS-26.5.2-arm64-arm-64bit-Mach-O",
134
+ "machine_arch": "arm64",
135
+ "macos": "26.5.2",
136
+ "model": "Qwen3.8-27B-MTPLX-Q4",
137
+ "timestamp": "2026-08-14T19:18:42-04:00"
138
+ }
139
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "local_files_only": false,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
25
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "Qwen2Tokenizer",
28
+ "tool_parser_type": "qwen3_coder",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>"
33
+ }