GraySoft
Projects Models About FAQ Contact Download guIDE →
Model Intelligence Sheet

teichai/qwen3-4b-thinking-2507-mimo-v2-flash-distill-gguf overview

This model was trained on a reasoning dataset of MiMo V2 Flash. --- This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library. An Ollama Modelfile is included for easy deployment.

ggufqwen3llama.cppagentunslothdataset:TeichAI/MiMo-V2-Flash-2300xbase_model:TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distillbase_model:quantized:TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distillendpoints_compatibleregion:usconversational
teichai/qwen3-4b-thinking-2507-mimo-v2-flash-distill-gguf visual
Downloads
6,717
Likes
4
Pipeline
Library
Visibility
Public
Access
Open

Repository Files & Downloads

13 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.bf16.gguf GGUF BF16 7.50 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.iq2_m.gguf GGUF IQ2_M 1.41 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.iq2_xs.gguf GGUF IQ2_XS 1.26 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.iq3_m.gguf GGUF IQ3_M 1.83 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.iq3_xs.gguf GGUF IQ3_XS 1.69 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.iq4_nl.gguf GGUF IQ4_NL 2.22 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.iq4_xs.gguf GGUF IQ4_XS 2.11 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.q3_k_m.gguf GGUF Q3_K_M 1.93 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.q3_k_s.gguf GGUF Q3_K_S 1.76 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.q4_k_m.gguf GGUF Q4_K_M 2.33 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.q5_k_m.gguf GGUF Q5_K_M 2.69 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.q6_k.gguf GGUF Q6_K 3.08 GB Download
Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill.q8_0.gguf GGUF 3.99 GB Download

Model Details Live

Model Slug
teichai/qwen3-4b-thinking-2507-mimo-v2-flash-distill-gguf
Author
TeichAI
Pipeline Task
Library
Created
2026-01-04
Last Modified
2026-01-04
Gated
No
Private
No
HF SHA
94b7996059e18428677b7f1eda1c2767285ed87d
License
Unknown
Language
Unknown
Base Model
TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "tags": [
      "gguf",
      "llama.cpp",
      "agent",
      "unsloth",
      "qwen3"
    ],
    "datasets": [
      "TeichAI/MiMo-V2-Flash-2300x"
    ],
    "base_model": [
      "TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill"
    ],
    "frontmatter": {
      "tags": [
        "gguf",
        "llama.cpp",
        "agent",
        "unsloth",
        "qwen3"
      ],
      "datasets": [
        "TeichAI/MiMo-V2-Flash-2300x"
      ],
      "base_model": [
        "TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill"
      ]
    },
    "hero_image_url": "",
    "summary": "This model was trained on a reasoning dataset of **MiMo V2 Flash**. --- This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library. An Ollama Modelfile is included for easy deployment.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\ntags:\n- gguf\n- llama.cpp\n- agent\n- unsloth\n- qwen3\ndatasets:\n- TeichAI/MiMo-V2-Flash-2300x\nbase_model:\n- TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill\n---\n\n# Qwen3 4B Thinking 2507 - MiMo V2 Flash Distill\n\nThis model was trained on a reasoning dataset of **MiMo V2 Flash**.\n\n- 🧬 Datasets:\n  - `TeichAI/MiMo-V2-Flash-2300x`\n\n- 🏗 Base Model:\n  - `unsloth/Qwen3-4B-Thinking-2507`\n \n- ⚡ Use cases:\n  - Coding\n  - Science\n  - Chat\n  - Deep Research\n\n- ∑ Stats (Dataset)\n  - Costs: $ 0.00 (USD)\n  - Total tokens (input + output): 7.36 M\n---\n\nThis qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.\n\nAn Ollama Modelfile is included for easy deployment.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "qwen3",
    "llama.cpp",
    "agent",
    "unsloth",
    "dataset:TeichAI/MiMo-V2-Flash-2300x",
    "base_model:TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill",
    "base_model:quantized:TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 4,
  "downloads": 6717,
  "gated": false,
  "private": false,
  "last_modified": "2026-01-04T22:02:55.000Z",
  "created_at": "2026-01-04T02:47:03.000Z",
  "pipeline_tag": "",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "6959d4a7e7e1bed6d739e002",
  "id": "TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill-GGUF",
  "modelId": "TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill-GGUF",
  "sha": "94b7996059e18428677b7f1eda1c2767285ed87d",
  "createdAt": "2026-01-04T02:47:03.000Z",
  "lastModified": "2026-01-04T22:02:55.000Z",
  "author": "TeichAI",
  "downloads": 6717,
  "likes": 4,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 17
}