github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15681] Missing reasoning output with gemma4:26b-mxfp8 #35764

New Issue
Open
opened 2026-04-22 20:26:58 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 20:26:58 -05:00
Owner
Copy Link

Originally created by @Archiklein on GitHub (Apr 18, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15681

What is the issue?

When running gemma4:26b-mxfp8 through /api/generate or Ollama Python ollama.Client.generate() the response does not contain any thinking text. Only once "think" is set to True the thinking text is being returned. Even though the model is reasoning by default.

Running the same response through the OpenAI compatibility API however does return reasoning text.

without "think" parameter

"response": "Moin! Wie kann ich dir heute helfen?"
"eval_count": 277 <-- clearly indicating the hidden reasoning in comparison to the response

with "think" = true

"response":"Moin! Wie kann ich dir heute helfen?"
"thinking":""Moin" (Northern German/Low German greeting).\nInformal, friendly, regional.\nRespond appropriately to a greeting in a similar tone.\n\n * "Moin" can be used at any time of day (not just morning).\n * Typical responses: "Moin!", "Moin moin!", "Moin, wie geht's?", or just a friendly greeting in English if the user prefers, but sticking to the vibe is better.\n\n * Option 1 (Traditional/Regional): "Moin! Wie kann ich dir heute helfen?" (Moin! How can I help you today?)\n * Option 2 (Casual): "Moin moin! Was gibt's?" (Moin moin! What's up?)\n * Option 3 (Bilingual/Helpful): "Moin! How can I help you today?"\n\n * Acknowledge the greeting.\n * Offer assistance.\n\n Draft: "Moin! Wie kann ich dir heute helfen?" (Simple, polite, matches the tone)."
"eval_count":251

through OpenAI API

"content": "Moin! Wie kann ich dir heute helfen?"
"reasoning": ""Moin" (Northern German greeting).\nStandard greeting, informal/semi-formal, friendly.\nRespond appropriately to reflect the same vibe (friendly, perhaps using northern German style if appropriate, or standard German/English).\n\n * Option 1 (Northern German): "Moin moin!" (Very common).\n * Option 2 (Standard German): "Hallo! Wie kann ich dir helfen?" (Helpful AI persona).\n * Option 3 (Bilingual/Mixed): "Moin! Wie geht's? Wie kann ich dir heute helfen?"\n\n * Since the user spoke in Northern German dialect, responding with a friendly "Moin!" or "Moin moin!" builds rapport.\n * Follow up with a polite inquiry about how I can assist.\n\n * "Moin! Wie kann ich dir heute helfen?" (Simple and effective).\n * "Moin moin! Alles klar bei dir? Was kann ich f\u00fcr dich tun?" (More casual).\n\n"Moin! Wie kann ich dir heute helfen?" (Short, friendly, professional)."
"total_tokens": 272

Relevant log output

# without "think" parameter

curl http://localhost:11434/api/generate -d '{
  "model": "gemma4:26b-mxfp8",
  "prompt": "Moin",
  "stream": false,
  "keep_alive": "1m"
}'

{
  "model": "gemma4:26b-mxfp8",
  "created_at": "2026-04-18T20:26:51.336928Z",
  "response": "Moin! Wie kann ich dir heute helfen?",
  "done": true,
  "done_reason": "stop",
  "context": [
    2,
    105,
    9731,
    107,
    98,
    107,
    106,
    107,
    105,
    2364,
    107,
    236792,
    3077,
    106,
    107,
    105,
    4368,
    107,
    100,
    45518,
    107,
    236829,
    139,
    4661,
    236787,
    623,
    236792,
    3077,
    236775,
    107,
    140,
    236829,
    139,
    28040,
    236787,
    14533,
    9115,
    568,
    2740,
    1667,
    198188,
    236768,
    965,
    15632,
    9115,
    44852,
    236761,
    107,
    140,
    236829,
    139,
    146868,
    236787,
    562,
    3364,
    26227,
    1456,
    528,
    15632,
    9405,
    236764,
    6590,
    623,
    9259,
    236775,
    653,
    623,
    11947,
    5597,
    236775,
    568,
    3480,
    625,
    740,
    577,
    1456,
    36448,
    769,
    108,
    140,
    236829,
    139,
    136408,
    1063,
    528,
    496,
    3361,
    15737,
    236786,
    3061,
    236761,
    107,
    140,
    236829,
    139,
    8755,
    236787,
    107,
    144,
    236829,
    139,
    21108,
    9115,
    236787,
    623,
    45890,
    9332,
    653,
    623,
    236823,
    11125,
    19653,
    9332,
    568,
    236776,
    3103,
    10781,
    236786,
    540,
    2642,
    769,
    107,
    144,
    236829,
    139,
    26834,
    9115,
    236787,
    623,
    236792,
    3077,
    9332,
    568,
    39905,
    236764,
    10841,
    769,
    107,
    144,
    236829,
    139,
    193760,
    236787,
    623,
    236792,
    3077,
    520,
    3077,
    9332,
    568,
    26546,
    3364,
    769,
    107,
    144,
    236829,
    139,
    28368,
    1275,
    236786,
    4098,
    236772,
    29963,
    236787,
    623,
    236792,
    3077,
    236888,
    33038,
    10492,
    6838,
    6557,
    34306,
    75471,
    7462,
    568,
    21108,
    12498,
    3072,
    769,
    108,
    140,
    236829,
    139,
    10081,
    506,
    2430,
    1456,
    496,
    44852,
    236772,
    15396,
    26227,
    236764,
    35136,
    607,
    623,
    236792,
    3077,
    9332,
    653,
    623,
    236792,
    3077,
    520,
    3077,
    9332,
    14004,
    496,
    2480,
    2430,
    2707,
    236761,
    107,
    140,
    236829,
    139,
    51613,
    496,
    11045,
    1500,
    236772,
    1048,
    2934,
    563,
    4077,
    573,
    614,
    12498,
    236761,
    108,
    140,
    236829,
    139,
    236775,
    236792,
    3077,
    236888,
    33038,
    10492,
    6838,
    6557,
    34306,
    75471,
    7462,
    568,
    83899,
    532,
    5707,
    769,
    107,
    140,
    236829,
    139,
    236775,
    236792,
    3077,
    520,
    3077,
    236888,
    15141,
    10492,
    6838,
    4591,
    16142,
    8750,
    7462,
    568,
    9474,
    15189,
    769,
    108,
    140,
    236775,
    236792,
    3077,
    236888,
    33038,
    10492,
    6838,
    6557,
    34306,
    75471,
    7462,
    101,
    236792,
    3077,
    236888,
    33038,
    10492,
    6838,
    6557,
    34306,
    75471,
    236881
  ],
  "total_duration": 6171523125,
  "load_duration": 2355890666,
  "prompt_eval_count": 18,
  "prompt_eval_duration": 272332500,
  "eval_count": 277,
  "eval_duration": 3542885500
}

# with "think" = true

curl http://localhost:11434/api/generate -d '{
  "model": "gemma4:26b-mxfp8",
  "prompt": "Moin",
  "stream": false,
  "think": true 
}'

{
  "model":"gemma4:26b-mxfp8",
  "created_at":"2026-04-18T20:14:40.276288Z",
  "response":"Moin! Wie kann ich dir heute helfen?",
  "thinking":"\"Moin\" (Northern German/Low German greeting).\nInformal, friendly, regional.\nRespond appropriately to a greeting in a similar tone.\n\n    *   \"Moin\" can be used at any time of day (not just morning).\n    *   Typical responses: \"Moin!\", \"Moin moin!\", \"Moin, wie geht's?\", or just a friendly greeting in English if the user prefers, but sticking to the vibe is better.\n\n    *   *Option 1 (Traditional/Regional):* \"Moin! Wie kann ich dir heute helfen?\" (Moin! How can I help you today?)\n    *   *Option 2 (Casual):* \"Moin moin! Was gibt's?\" (Moin moin! What's up?)\n    *   *Option 3 (Bilingual/Helpful):* \"Moin! How can I help you today?\"\n\n    *   Acknowledge the greeting.\n    *   Offer assistance.\n\n    *Draft:* \"Moin! Wie kann ich dir heute helfen?\" (Simple, polite, matches the tone).",
  "done":true,
  "done_reason":"stop",
  "context": [2,105,9731,107,98,107,106,107,105,2364,107,236792,3077,106,107,105,4368,107,100,45518,107,236775,236792,3077,236775,568,72982,9115,236786,26834,9115,26227,769,107,57719,514,236764,10841,236764,10969,236761,107,118904,37404,531,496,26227,528,496,3361,15737,236761,108,140,236829,139,236775,236792,3077,236775,740,577,1456,657,1027,990,529,1719,568,2217,1164,5597,769,107,140,236829,139,105330,13630,236787,623,236792,3077,41218,623,236792,3077,520,3077,41218,623,236792,3077,236764,8880,30511,236789,236751,32109,653,1164,496,10841,26227,528,5422,768,506,2430,62197,236764,840,44640,531,506,44249,563,2480,236761,108,140,236829,139,236829,13733,236743,236770,568,63190,236786,98472,1473,236829,623,236792,3077,236888,33038,10492,6838,6557,34306,75471,7462,568,236792,3077,236888,2088,740,564,1601,611,3124,17103,107,140,236829,139,236829,13733,236743,236778,568,193760,1473,236829,623,236792,3077,520,3077,236888,15141,20780,236789,236751,7462,568,236792,3077,520,3077,236888,2900,236789,236751,872,17103,107,140,236829,139,236829,13733,236743,236800,568,236799,53300,236786,28368,1275,1473,236829,623,236792,3077,236888,2088,740,564,1601,611,3124,7462,108,140,236829,139,236776,11190,3811,506,26227,236761,107,140,236829,139,77422,10686,236761,108,140,236829,88293,149681,623,236792,3077,236888,33038,10492,6838,6557,34306,75471,7462,568,22575,236764,54651,236764,12853,506,15737,769,101,236792,3077,236888,33038,10492,6838,6557,34306,75471,236881],
  "total_duration":3621962750,
  "load_duration":52653958,
  "prompt_eval_count":18,
  "prompt_eval_duration":342545333,
  "eval_count":251,
  "eval_duration":3226313625
}


# through OpenAI API

curl -X POST http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
  "model": "gemma4:26b-mxfp8",
  "messages": [
    {
      "role": "user",
      "content": "Moin"
    }
  ]
}'

{
  "id": "chatcmpl-648",
  "object": "chat.completion",
  "created": 1776545076,
  "model": "gemma4:26b-mxfp8",
  "system_fingerprint": "fp_ollama",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Moin! Wie kann ich dir heute helfen?",
        "reasoning": "\"Moin\" (Northern German greeting).\nStandard greeting, informal/semi-formal, friendly.\nRespond appropriately to reflect the same vibe (friendly, perhaps using northern German style if appropriate, or standard German/English).\n\n    *   *Option 1 (Northern German):* \"Moin moin!\" (Very common).\n    *   *Option 2 (Standard German):* \"Hallo! Wie kann ich dir helfen?\" (Helpful AI persona).\n    *   *Option 3 (Bilingual/Mixed):* \"Moin! Wie geht's? Wie kann ich dir heute helfen?\"\n\n    *   Since the user spoke in Northern German dialect, responding with a friendly \"Moin!\" or \"Moin moin!\" builds rapport.\n    *   Follow up with a polite inquiry about how I can assist.\n\n    *   \"Moin! Wie kann ich dir heute helfen?\" (Simple and effective).\n    *   \"Moin moin! Alles klar bei dir? Was kann ich f\u00fcr dich tun?\" (More casual).\n\n\"Moin! Wie kann ich dir heute helfen?\" (Short, friendly, professional)."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 254,
    "total_tokens": 272
  }
}

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.21.0

Originally created by @Archiklein on GitHub (Apr 18, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15681 ### What is the issue? When running gemma4:26b-mxfp8 through /api/generate or Ollama Python ollama.Client.generate() the response does not contain any thinking text. Only once "think" is set to True the thinking text is being returned. Even though the model is reasoning by default. Running the same response through the OpenAI compatibility API however does return reasoning text. # without "think" parameter "response": "Moin! Wie kann ich dir heute helfen?" "eval_count": 277 <-- clearly indicating the hidden reasoning in comparison to the response # with "think" = true "response":"Moin! Wie kann ich dir heute helfen?" "thinking":"\"Moin\" (Northern German/Low German greeting).\nInformal, friendly, regional.\nRespond appropriately to a greeting in a similar tone.\n\n * \"Moin\" can be used at any time of day (not just morning).\n * Typical responses: \"Moin!\", \"Moin moin!\", \"Moin, wie geht's?\", or just a friendly greeting in English if the user prefers, but sticking to the vibe is better.\n\n * *Option 1 (Traditional/Regional):* \"Moin! Wie kann ich dir heute helfen?\" (Moin! How can I help you today?)\n * *Option 2 (Casual):* \"Moin moin! Was gibt's?\" (Moin moin! What's up?)\n * *Option 3 (Bilingual/Helpful):* \"Moin! How can I help you today?\"\n\n * Acknowledge the greeting.\n * Offer assistance.\n\n *Draft:* \"Moin! Wie kann ich dir heute helfen?\" (Simple, polite, matches the tone)." "eval_count":251 # through OpenAI API "content": "Moin! Wie kann ich dir heute helfen?" "reasoning": "\"Moin\" (Northern German greeting).\nStandard greeting, informal/semi-formal, friendly.\nRespond appropriately to reflect the same vibe (friendly, perhaps using northern German style if appropriate, or standard German/English).\n\n * *Option 1 (Northern German):* \"Moin moin!\" (Very common).\n * *Option 2 (Standard German):* \"Hallo! Wie kann ich dir helfen?\" (Helpful AI persona).\n * *Option 3 (Bilingual/Mixed):* \"Moin! Wie geht's? Wie kann ich dir heute helfen?\"\n\n * Since the user spoke in Northern German dialect, responding with a friendly \"Moin!\" or \"Moin moin!\" builds rapport.\n * Follow up with a polite inquiry about how I can assist.\n\n * \"Moin! Wie kann ich dir heute helfen?\" (Simple and effective).\n * \"Moin moin! Alles klar bei dir? Was kann ich f\u00fcr dich tun?\" (More casual).\n\n\"Moin! Wie kann ich dir heute helfen?\" (Short, friendly, professional)." "total_tokens": 272 ### Relevant log output ```shell # without "think" parameter curl http://localhost:11434/api/generate -d '{ "model": "gemma4:26b-mxfp8", "prompt": "Moin", "stream": false, "keep_alive": "1m" }' { "model": "gemma4:26b-mxfp8", "created_at": "2026-04-18T20:26:51.336928Z", "response": "Moin! Wie kann ich dir heute helfen?", "done": true, "done_reason": "stop", "context": [ 2, 105, 9731, 107, 98, 107, 106, 107, 105, 2364, 107, 236792, 3077, 106, 107, 105, 4368, 107, 100, 45518, 107, 236829, 139, 4661, 236787, 623, 236792, 3077, 236775, 107, 140, 236829, 139, 28040, 236787, 14533, 9115, 568, 2740, 1667, 198188, 236768, 965, 15632, 9115, 44852, 236761, 107, 140, 236829, 139, 146868, 236787, 562, 3364, 26227, 1456, 528, 15632, 9405, 236764, 6590, 623, 9259, 236775, 653, 623, 11947, 5597, 236775, 568, 3480, 625, 740, 577, 1456, 36448, 769, 108, 140, 236829, 139, 136408, 1063, 528, 496, 3361, 15737, 236786, 3061, 236761, 107, 140, 236829, 139, 8755, 236787, 107, 144, 236829, 139, 21108, 9115, 236787, 623, 45890, 9332, 653, 623, 236823, 11125, 19653, 9332, 568, 236776, 3103, 10781, 236786, 540, 2642, 769, 107, 144, 236829, 139, 26834, 9115, 236787, 623, 236792, 3077, 9332, 568, 39905, 236764, 10841, 769, 107, 144, 236829, 139, 193760, 236787, 623, 236792, 3077, 520, 3077, 9332, 568, 26546, 3364, 769, 107, 144, 236829, 139, 28368, 1275, 236786, 4098, 236772, 29963, 236787, 623, 236792, 3077, 236888, 33038, 10492, 6838, 6557, 34306, 75471, 7462, 568, 21108, 12498, 3072, 769, 108, 140, 236829, 139, 10081, 506, 2430, 1456, 496, 44852, 236772, 15396, 26227, 236764, 35136, 607, 623, 236792, 3077, 9332, 653, 623, 236792, 3077, 520, 3077, 9332, 14004, 496, 2480, 2430, 2707, 236761, 107, 140, 236829, 139, 51613, 496, 11045, 1500, 236772, 1048, 2934, 563, 4077, 573, 614, 12498, 236761, 108, 140, 236829, 139, 236775, 236792, 3077, 236888, 33038, 10492, 6838, 6557, 34306, 75471, 7462, 568, 83899, 532, 5707, 769, 107, 140, 236829, 139, 236775, 236792, 3077, 520, 3077, 236888, 15141, 10492, 6838, 4591, 16142, 8750, 7462, 568, 9474, 15189, 769, 108, 140, 236775, 236792, 3077, 236888, 33038, 10492, 6838, 6557, 34306, 75471, 7462, 101, 236792, 3077, 236888, 33038, 10492, 6838, 6557, 34306, 75471, 236881 ], "total_duration": 6171523125, "load_duration": 2355890666, "prompt_eval_count": 18, "prompt_eval_duration": 272332500, "eval_count": 277, "eval_duration": 3542885500 } # with "think" = true curl http://localhost:11434/api/generate -d '{ "model": "gemma4:26b-mxfp8", "prompt": "Moin", "stream": false, "think": true }' { "model":"gemma4:26b-mxfp8", "created_at":"2026-04-18T20:14:40.276288Z", "response":"Moin! Wie kann ich dir heute helfen?", "thinking":"\"Moin\" (Northern German/Low German greeting).\nInformal, friendly, regional.\nRespond appropriately to a greeting in a similar tone.\n\n * \"Moin\" can be used at any time of day (not just morning).\n * Typical responses: \"Moin!\", \"Moin moin!\", \"Moin, wie geht's?\", or just a friendly greeting in English if the user prefers, but sticking to the vibe is better.\n\n * *Option 1 (Traditional/Regional):* \"Moin! Wie kann ich dir heute helfen?\" (Moin! How can I help you today?)\n * *Option 2 (Casual):* \"Moin moin! Was gibt's?\" (Moin moin! What's up?)\n * *Option 3 (Bilingual/Helpful):* \"Moin! How can I help you today?\"\n\n * Acknowledge the greeting.\n * Offer assistance.\n\n *Draft:* \"Moin! Wie kann ich dir heute helfen?\" (Simple, polite, matches the tone).", "done":true, "done_reason":"stop", "context": [2,105,9731,107,98,107,106,107,105,2364,107,236792,3077,106,107,105,4368,107,100,45518,107,236775,236792,3077,236775,568,72982,9115,236786,26834,9115,26227,769,107,57719,514,236764,10841,236764,10969,236761,107,118904,37404,531,496,26227,528,496,3361,15737,236761,108,140,236829,139,236775,236792,3077,236775,740,577,1456,657,1027,990,529,1719,568,2217,1164,5597,769,107,140,236829,139,105330,13630,236787,623,236792,3077,41218,623,236792,3077,520,3077,41218,623,236792,3077,236764,8880,30511,236789,236751,32109,653,1164,496,10841,26227,528,5422,768,506,2430,62197,236764,840,44640,531,506,44249,563,2480,236761,108,140,236829,139,236829,13733,236743,236770,568,63190,236786,98472,1473,236829,623,236792,3077,236888,33038,10492,6838,6557,34306,75471,7462,568,236792,3077,236888,2088,740,564,1601,611,3124,17103,107,140,236829,139,236829,13733,236743,236778,568,193760,1473,236829,623,236792,3077,520,3077,236888,15141,20780,236789,236751,7462,568,236792,3077,520,3077,236888,2900,236789,236751,872,17103,107,140,236829,139,236829,13733,236743,236800,568,236799,53300,236786,28368,1275,1473,236829,623,236792,3077,236888,2088,740,564,1601,611,3124,7462,108,140,236829,139,236776,11190,3811,506,26227,236761,107,140,236829,139,77422,10686,236761,108,140,236829,88293,149681,623,236792,3077,236888,33038,10492,6838,6557,34306,75471,7462,568,22575,236764,54651,236764,12853,506,15737,769,101,236792,3077,236888,33038,10492,6838,6557,34306,75471,236881], "total_duration":3621962750, "load_duration":52653958, "prompt_eval_count":18, "prompt_eval_duration":342545333, "eval_count":251, "eval_duration":3226313625 } # through OpenAI API curl -X POST http://localhost:11434/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "gemma4:26b-mxfp8", "messages": [ { "role": "user", "content": "Moin" } ] }' { "id": "chatcmpl-648", "object": "chat.completion", "created": 1776545076, "model": "gemma4:26b-mxfp8", "system_fingerprint": "fp_ollama", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Moin! Wie kann ich dir heute helfen?", "reasoning": "\"Moin\" (Northern German greeting).\nStandard greeting, informal/semi-formal, friendly.\nRespond appropriately to reflect the same vibe (friendly, perhaps using northern German style if appropriate, or standard German/English).\n\n * *Option 1 (Northern German):* \"Moin moin!\" (Very common).\n * *Option 2 (Standard German):* \"Hallo! Wie kann ich dir helfen?\" (Helpful AI persona).\n * *Option 3 (Bilingual/Mixed):* \"Moin! Wie geht's? Wie kann ich dir heute helfen?\"\n\n * Since the user spoke in Northern German dialect, responding with a friendly \"Moin!\" or \"Moin moin!\" builds rapport.\n * Follow up with a polite inquiry about how I can assist.\n\n * \"Moin! Wie kann ich dir heute helfen?\" (Simple and effective).\n * \"Moin moin! Alles klar bei dir? Was kann ich f\u00fcr dich tun?\" (More casual).\n\n\"Moin! Wie kann ich dir heute helfen?\" (Short, friendly, professional)." }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 18, "completion_tokens": 254, "total_tokens": 272 } } ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.21.0
GiteaMirror added the bug label 2026-04-22 20:26:58 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#35764
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?