Mungert/MiMo-VL-7B-SFT-GGUF

MiMo-VL-7B-SFT GGUF Models

Model Generation Details

This model was generated using llama.cpp at commit 71bdbdb5.

Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit)

Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on Llama-3-8B. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency.

Benchmark Context

All tests conducted on Llama-3-8B-Instruct using:

• Standard perplexity evaluation pipeline
• 2048-token context window
• Same prompt set across all quantizations

Method

• Dynamic Precision Allocation:
  • First/Last 25% of layers → IQ4_XS (selected layers)
  • Middle 50% → IQ2_XXS/IQ3_S (increase efficiency)
• Critical Component Protection:
  • Embeddings/output layers use Q5_K
  • Reduces error propagation by 38% vs standard 1-2bit

Quantization Performance Comparison (Llama-3-8B)

Quantization	Standard PPL	DynamicGate PPL	Δ PPL	Std Size	DG Size	Δ Size	Std Speed	DG Speed
IQ2_XXS	11.30	9.84	-12.9%	2.5G	2.6G	+0.1G	234s	246s
IQ2_XS	11.72	11.63	-0.8%	2.7G	2.8G	+0.1G	242s	246s
IQ2_S	14.31	9.02	-36.9%	2.7G	2.9G	+0.2G	238s	244s
IQ1_M	27.46	15.41	-43.9%	2.2G	2.5G	+0.3G	206s	212s
IQ1_S	53.07	32.00	-39.7%	2.1G	2.4G	+0.3G	184s	209s

Key:

• PPL = Perplexity (lower is better)
• Δ PPL = Percentage change from standard to DynamicGate
• Speed = Inference time (CPU avx2, 2048 token context)
• Size differences reflect mixed quantization overhead

Key Improvements:

• 🔥 IQ1_M shows massive 43.9% perplexity reduction (27.46 → 15.41)
• 🚀 IQ2_S cuts perplexity by 36.9% while adding only 0.2GB
• ⚡ IQ1_S maintains 39.7% better accuracy despite 1-bit quantization

Tradeoffs:

• All variants have modest size increases (0.1-0.3GB)
• Inference speeds remain comparable (<5% difference)

When to Use These Models

📌 Fitting models into GPU VRAM

✔ Memory-constrained deployments

✔ Cpu and Edge Devices where 1-2bit errors can be tolerated

✔ Research into ultra-low-bit quantization

Choosing the Right Model Format

Selecting the correct model format depends on your hardware capabilities and memory constraints.

BF16 (Brain Float 16) – Use if BF16 acceleration is available

• A 16-bit floating-point format designed for faster computation while retaining good precision.
• Provides similar dynamic range as FP32 but with lower memory usage.
• Recommended if your hardware supports BF16 acceleration (check your device's specs).
• Ideal for high-performance inference with reduced memory footprint compared to FP32.

📌 Use BF16 if:
✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs).
✔ You want higher precision while saving memory.
✔ You plan to requantize the model into another format.

📌 Avoid BF16 if:
❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower).
❌ You need compatibility with older devices that lack BF16 optimization.

---

F16 (Float 16) – More widely supported than BF16

• A 16-bit floating-point high precision but with less of range of values than BF16.
• Works on most devices with FP16 acceleration support (including many GPUs and some CPUs).
• Slightly lower numerical precision than BF16 but generally sufficient for inference.

📌 Use F16 if:
✔ Your hardware supports FP16 but not BF16.
✔ You need a balance between speed, memory usage, and accuracy.
✔ You are running on a GPU or another device optimized for FP16 computations.

📌 Avoid F16 if:
❌ Your device lacks native FP16 support (it may run slower than expected).
❌ You have memory limitations.

---

Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference

Quantization reduces model size and memory usage while maintaining as much accuracy as possible.

• Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision.
• Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory.

📌 Use Quantized Models if:
✔ You are running inference on a CPU and need an optimized model.
✔ Your device has low VRAM and cannot load full-precision models.
✔ You want to reduce memory footprint while keeping reasonable accuracy.

📌 Avoid Quantized Models if:
❌ You need maximum accuracy (full-precision models are better for this).
❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).

---

Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)

These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint.

• IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency.

  • Use case: Best for ultra-low-memory devices where even Q4_K is too large.
  • Trade-off: Lower accuracy compared to higher-bit quantizations.

• IQ3_S: Small block size for maximum memory efficiency.

  • Use case: Best for low-memory devices where IQ3_XS is too aggressive.

• IQ3_M: Medium block size for better accuracy than IQ3_S.

  • Use case: Suitable for low-memory devices where IQ3_S is too limiting.

• Q4_K: 4-bit quantization with block-wise optimization for better accuracy.

  • Use case: Best for low-memory devices where Q6_K is too large.

• Q4_0: Pure 4-bit quantization, optimized for ARM devices.

  • Use case: Best for ARM-based devices or low-memory environments.

---

Summary Table: Model Format Selection

Model Format	Precision	Memory Usage	Device Requirements	Best Use Case
BF16	Highest	High	BF16-supported GPU/CPUs	High-speed inference with reduced memory
F16	High	High	FP16-supported devices	GPU inference when BF16 isn't available
Q4_K	Medium Low	Low	CPU or Low-VRAM devices	Best for memory-constrained environments
Q6_K	Medium	Moderate	CPU with more memory	Better accuracy while still being quantized
Q8_0	High	Moderate	CPU or GPU with enough VRAM	Best accuracy among quantized models
IQ3_XS	Very Low	Very Low	Ultra-low-memory devices	Extreme memory efficiency and low accuracy
Q4_0	Low	Low	ARM or low-memory devices	llama.cpp can optimize for ARM devices

---

Included Files & Details

MiMo-VL-7B-SFT-bf16.gguf

• Model weights preserved in BF16.
• Use this if you want to requantize the model into a different format.
• Best if your device supports BF16 acceleration.

MiMo-VL-7B-SFT-f16.gguf

• Model weights stored in F16.
• Use if your device supports FP16, especially if BF16 is not available.

MiMo-VL-7B-SFT-bf16-q8_0.gguf

• Output & embeddings remain in BF16.
• All other layers quantized to Q8_0.
• Use if your device supports BF16 and you want a quantized version.

MiMo-VL-7B-SFT-f16-q8_0.gguf

• Output & embeddings remain in F16.
• All other layers quantized to Q8_0.

MiMo-VL-7B-SFT-q4_k.gguf

• Output & embeddings quantized to Q8_0.
• All other layers quantized to Q4_K.
• Good for CPU inference with limited memory.

MiMo-VL-7B-SFT-q4_k_s.gguf

• Smallest Q4_K variant, using less memory at the cost of accuracy.
• Best for very low-memory setups.

MiMo-VL-7B-SFT-q6_k.gguf

• Output & embeddings quantized to Q8_0.
• All other layers quantized to Q6_K .

MiMo-VL-7B-SFT-q8_0.gguf

• Fully Q8 quantized model for better accuracy.
• Requires more memory but offers higher precision.

MiMo-VL-7B-SFT-iq3_xs.gguf

• IQ3_XS quantization, optimized for extreme memory efficiency.
• Best for ultra-low-memory devices.

MiMo-VL-7B-SFT-iq3_m.gguf

• IQ3_M quantization, offering a medium block size for better accuracy.
• Suitable for low-memory devices.

MiMo-VL-7B-SFT-q4_0.gguf

• Pure Q4_0 quantization, optimized for ARM devices.
• Best for low-memory environments.
• Prefer IQ4_NL for better accuracy.

🚀 If you find these models useful

❤ Please click "Like" if you find this useful!
Help me test my AI-Powered Network Monitor Assistant with quantum-ready security checks:
👉 Free Network Monitor

💬 How to test:
Choose an AI assistant type:

• TurboLLM (GPT-4o-mini)
• HugLLM (Hugginface Open-source)
• TestLLM (Experimental CPU-only)

What I’m Testing

I’m pushing the limits of small open-source models for AI network monitoring, specifically:

• Function calling against live network services
• How small can a model go while still handling:
  • Automated Nmap scans
  • Quantum-readiness checks
  • Network Monitoring tasks

🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads):

• ✅ Zero-configuration setup
• ⏳ 30s load time (slow inference but no API costs)
• 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4o-mini for:

• Create custom cmd processors to run .net code on Free Network Monitor Agents
• Real-time network diagnostics and monitoring
• Security Audits
• Penetration testing (Nmap/Metasploit)
• 🔑 Get more tokens by logging in or downloading our Free Network Monitor Agent with integrated AI Assistant

🔵 HugLLM – Latest Open-source models:

• 🌐 Runs on Hugging Face Inference API

💡 Example commands to you could test:

1. "Give me info on my websites SSL certificate"
2. "Check if my server is using quantum safe encyption for communication"
3. "Run a comprehensive security audit on my server"
4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Free Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution!

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
MiMo-VL Technical Report
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

| 🤗 HuggingFace  | 🤖️ ModelScope  | 📔 Technical Report  |

I. Introduction

In this report, we share our efforts to build a compact yet powerful VLM, MiMo-VL-7B. MiMo-VL-7B comprises (1) a native resolution ViT encoder that preserves fine-grained visual details, (2) an MLP projector for efficient cross-modal alignment, and (3) our MiMo-7B language model, specifically optimized for complex reasoning tasks.

The development of MiMo-VL-7B involves two sequential training processes: (1) A four-stage pre-training phase, which includes projector warmup, vision-language alignment, general multi-modal pre-training, and long-context Supervised Fine-Tuning (SFT). This phase yields the MiMo-VL-7B-SFT model. (2) A subsequent post-training phase, where we introduce Mixed On-policy Reinforcement Learning (MORL), a novel framework that seamlessly integrates diverse reward signals spanning perception accuracy, visual grounding precision, logical reasoning capabilities, and human/AI preferences. This phase yields the MiMo-VL-7B-RL model.

We open-source MiMo-VL-7B series, including checkpoints of the SFT and RL model. We believe this report along with the models will provide valuable insights to develop powerful reasoning VLMs that benefit the larger community.

🛤️ During this journey, we find

• Incorporating high-quality, broad-coverage reasoning data from the pre-training stage is crucial for enhancing model performance
  • We curate high-quality reasoning data by identifying diverse queries, employing large reasoning models to regenerate responses with long CoT, and applying rejection sampling to ensure quality.
  • Rather than treating this as supplementary fine-tuning data, we incorporate substantial volumes of this synthetic reasoning data directly into the later pre-training stages, where extended training yields continued performance improvements without saturation.
• Mixed On-policy Reinforcement Learning further enhances model performance, while achieving stable simultaneous improvements remains challenging
  • We apply RL across diverse capabilities, including reasoning, perception, grounding, and human preference alignment, spanning modalities including text, images, and videos. While this hybrid training approach further unlock model’s potential, interference across data domains remains a challenge.

II. Model Details

Models are available at Huggingface Collections: MiMo-VL and ModelScope Collections: MiMo-VL

Model	Description	Download (HuggingFace)	Download (ModelScope)
MiMo-VL-7B-SFT	VLM with extraordinary reasoning potential after 4-stage pre-training	🤗 XiaomiMiMo/MiMo-VL-7B-SFT	🤖️ XiaomiMiMo/MiMo-VL-7B-SFT
MiMo-VL-7B-RL	RL model leapfrogging existing open-source models	🤗 XiaomiMiMo/MiMo-VL-7B-RL	🤖️ XiaomiMiMo/MiMo-VL-7B-RL

III. Evaluation Results

General Capabilities

In general visual-language understanding, MiMo-VL-7B models achieve state-of-the-art open-source results.

Reasoning Tasks

In multi-modal reasoning, both the SFT and RL models significantly outperform all compared open-source baselines across these benchmarks.

Results marked with * are obtained using our evaluation framework. Tasks with ${\dagger}$ are evaluated by GPT-4o.

GUI Tasks

MiMo-VL-7B-RL possess exceptional GUI understanding and grounding capabilities. As a general-purpose VL model, MiMo-VL achieves comparable or even superior performance to GUI-specialized models.

Elo Rating

With our in-house evaluation dataset and GPT-4o judgments, MiMo-VL-7B-RL achieves the highest Elo rating among all evaluated open-source vision-language models, ranking first across models spanning from 7B to 72B parameters.

IV. Deployment

The MiMo-VL-7B series maintain full compatibility with the Qwen2_5_VLForConditionalGeneration architecture for deployment and inference.

V. Citation

@misc{coreteam2025mimovl,
      title={MiMo-VL Technical Report}, 
      author={{Xiaomi LLM-Core Team}},
      year={2025},
      url={https://github.com/XiaomiMiMo/MiMo-VL}, 
}

VI. Contact

Please contact us at [email protected] or open an issue if you have any questions.