DO

Dots.Llm1.Inst

DotsGGUF by unslothUpdated 2025-06-26
Download on Hugging Face
Parameters143B
Context32K
Layers62
Architecturedots1
Smallest quant48.0 GB
Quick answer

Dots.Llm1.Inst needs about 103.3 GB of memory at Q4_K_M (a 94.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 48.0 GB (TQ1_0) to 285.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 33.3 GB.

Dots.Llm1.Inst – a 142B‑parameter MoE model with 14B active parameters

Dots.Llm1.Inst is a 142B‑parameter MoE model that activates 14B parameters during inference. It supports a 32,768‑token context length and is released under the MIT license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Efficient parameter activation
  • High‑quality instruction tuning

Limits

  • Requires large VRAM for higher quantizations
  • No vision support
  • Limited language support to English and Chinese

Best for

  • Long‑form content generation
  • Complex reasoning tasks
  • Fine‑tuned instruction following

Who it’s for. Researchers and developers needing a high‑capacity MoE model with efficient inference. The model is suitable for those who can allocate sufficient GPU memory and are comfortable with GGUF quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_048.0 GB 56.8 GB
Too big Get file →
IQ1_S48.3 GB 57.1 GB
Too big Get file →
IQ1_M50.5 GB (2 parts) 59.3 GB
Too big Get file →
IQ2_XXS54.0 GB (2 parts) 62.8 GB
Too big Get file →
IQ2_M56.5 GB (2 parts) 65.3 GB
Too big Get file →
Q2_K58.1 GB (2 parts) 66.9 GB
Too big Get file →
Q2_K_L58.3 GB (2 parts) 67.1 GB
Too big Get file →
Q2_K_XL60.2 GB (2 parts) 69.0 GB
Too big Get file →
IQ3_XXS65.4 GB (2 parts) 74.3 GB
Too big Get file →
Q3_K_S67.7 GB (2 parts) 76.5 GB
Too big Get file →
Q3_K_XL69.6 GB (2 parts) 78.4 GB
Too big Get file →
Q3_K_M73.8 GB (2 parts) 82.6 GB
Too big Get file →
IQ4_XS77.6 GB (2 parts) 86.4 GB
Too big Get file →
IQ4_NL80.6 GB (2 parts) 89.4 GB
Too big Get file →
Q4_080.9 GB (2 parts) 89.7 GB
Too big Get file →
Q4_K_S86.5 GB (2 parts) 95.3 GB
Too big Get file →
Q4_K_XL86.8 GB (2 parts) 95.7 GB
Too big Get file →
Q4_189.5 GB (2 parts) 98.3 GB
Too big Get file →
Q4_K_M94.5 GB (2 parts) 103.3 GB
Too big Get file →
Q5_K_S101.2 GB (3 parts) 110.0 GB
Too big Get file →
Q5_K_M108.0 GB (3 parts) 116.8 GB
Too big Get file →
Q5_K_XL108.4 GB (3 parts) 117.3 GB
Too big Get file →
Q6_K128.1 GB (3 parts) 137.0 GB
Too big Get file →
Q6_K_XL131.2 GB (3 parts) 140.0 GB
Too big Get file →
Q8_0151.8 GB (4 parts) 160.6 GB
Too big Get file →
Q8_K_XL162.2 GB (4 parts) 171.0 GB
Too big Get file →
BF16285.6 GB (6 parts) 294.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 80.87 GB, memory 89.7 GB at 8k context). For 12 GB VRAM, Q4_K_S (86.52 GB, 95.3 GB) or Q4_K_XL (86.84 GB, 95.7 GB) are options. For 16 GB VRAM, Q5_K_S (101.17 GB, 110 GB) or Q5_K_M (107.99 GB, 116.8 GB) can be considered. Estimates are approximate.

What GPU do you need for Dots.Llm1.Inst?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Dots.Llm1.Inst quant should you choose?

Q4_K_M is the usual starting point for Dots.Llm1.Inst: it balances file size and quality well. Here it is a 94.5 GB file.

The Q8_0 file is 151.8 GB, about 1.6 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 TQ1_0 at 48.0 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedots1
Parameters143B (approximate, mixture of experts)
Layers62
Trained context32,768 tokens
KV cache (fp16)992 KB per token

Source

Quantized byunsloth
FamilyDots
Licensemit
Downloads (HF)1,980
Last updated2025-06-26

Frequently asked questions about Dots.Llm1.Inst

How much VRAM does Dots.Llm1.Inst need?

About 103.3 GB at Q4_K_M with an 8K context window. That is the 94.5 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 Dots.Llm1.Inst on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 56.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dots.Llm1.Inst GGUF?

It depends on the quant: TQ1_0 is 48.0 GB, IQ1_S is 48.3 GB, IQ1_M is 50.5 GB, IQ2_XXS is 54.0 GB, IQ2_M is 56.5 GB, Q2_K is 58.1 GB and 21 more.

What context length does Dots.Llm1.Inst support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 8.3 GB at 8K and 33.3 GB at 32K.

Where can I download Dots.Llm1.Inst GGUF?

The files are on Hugging Face in the unsloth/dots.llm1.inst-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 Dots.Llm1.Inst use?

Hugging Face lists the license as mit. 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 Dots.Llm1.Inst on 8 GB VRAM?

Only the lowest‑bit quantizations such as Q4_0 or Q4_K_S can fit, but they still require around 90 GB of VRAM at 8k context, so 8 GB is insufficient.

Does the model support Chinese?

Yes, the model supports English and Chinese languages.

Is there a vision capability?

No, the model does not include vision support.

Other GGUFs of dots.llm1.inst

Similar models

Browse all →

More from unsloth

All by unsloth →

More Dots models

All Dots →

Other large models

All large models →