MI

MiniMax-M2.7-DFlash

MinimaxGGUF by AnbeeldUpdated 2026-08-29
Download on Hugging Face
Parameters1.31B
Context192K
Layers5
Architecturedflash
Smallest quant0.5 GB
Quick answer

MiniMax-M2.7-DFlash needs about 2.0 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.5 GB (Q2_K) to 2.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

MiniMax-M2.7-DFlash: 1.31B parameter lightweight drafter model

MiniMax-M2.7-DFlash is a 1.31B parameter dflash architecture model designed for parallel token drafting. It is a drafter that must be paired with MiniMax-M2.7. The model supports a context length of 196608 tokens.

Good at

  • Parallel token drafting
  • Lightweight inference
  • Large context support

Limits

  • No vision support
  • Requires pairing with MiniMax-M2.7
  • License type is other

Best for

  • Drafting multiple tokens in parallel
  • Low‑memory inference
  • Large‑context text generation

Who it’s for. Developers building custom LLM pipelines that need efficient token drafting. Researchers exploring speculative decoding methods. Users who require a lightweight drafter to pair with a larger model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.5 GB 1.7 GB
Fits Get file →
Q3_K_M0.6 GB 1.8 GB
Fits Get file →
Q4_K_M0.8 GB 2.0 GB
Fits Get file →
Q5_K_M0.9 GB 2.1 GB
Fits Get file →
Q6_K1.1 GB 2.3 GB
Fits Get file →
Q8_01.4 GB 2.6 GB
Fits Get file →
BF162.6 GB 3.8 GB
Fits Get file →

For 8 GB VRAM, Q2_K (0.49 GB, 1.7 GB memory) is recommended. For 12 GB VRAM, Q3_K_M (0.64 GB, 1.8 GB memory) or Q4_K_M (0.79 GB, 2 GB memory) are suitable. Higher precision quants increase accuracy but require more memory.

What GPU do you need for MiniMax-M2.7-DFlash?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is BF16 (2.6 GB file, about 3.8 GB in use).

Which MiniMax-M2.7-DFlash quant should you choose?

Q4_K_M is the usual starting point for MiniMax-M2.7-DFlash: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.4 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters1.31B
Layers5
Trained context196,608 tokens
KV cache (fp16)80 KB per token

Source

Quantized byAnbeeld
FamilyMinimax
Licenseother
Downloads (HF)614
Last updated2026-08-29

Frequently asked questions about MiniMax-M2.7-DFlash

How much VRAM does MiniMax-M2.7-DFlash need?

About 2.0 GB at Q4_K_M with an 8K context window. That is the 0.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run MiniMax-M2.7-DFlash on an 8 GB GPU?

Yes, with BF16: the 2.6 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniMax-M2.7-DFlash GGUF?

It depends on the quant: Q2_K is 0.5 GB, Q3_K_M is 0.6 GB, Q4_K_M is 0.8 GB, Q5_K_M is 0.9 GB, Q6_K is 1.1 GB, Q8_0 is 1.4 GB and 1 more.

What context length does MiniMax-M2.7-DFlash support?

The GGUF header lists a trained context length of 196,608 tokens (192K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download MiniMax-M2.7-DFlash GGUF?

The files are on Hugging Face in the Anbeeld/MiniMax-M2.7-DFlash-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does MiniMax-M2.7-DFlash use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run MiniMax-M2.7-DFlash on 8 GB VRAM?

Yes, the Q2_K quant uses 0.49 GB file size and approximately 1.7 GB VRAM at 8 k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports up to 196608 tokens of context.

Similar models

Browse all →

More from Anbeeld

All by Anbeeld →

More Minimax models

All Minimax →

Other tiny models

All tiny models →