MI

Dumpling Mistral Nemo 8B i1

MistralGGUF by mradermacherUpdated 2025-02-12
Download on Hugging Face
Parameters8.43B
Context1000K
Layers26
Architecturellama
Smallest quant2.2 GB
Quick answer

Dumpling Mistral Nemo 8B i1 needs about 6.6 GB of memory at Q4_K_M (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 2.2 GB (IQ1_S) to 6.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.

Dumpling Mistral Nemo 8B i1 – a 8.43B‑parameter Mistral model fine‑tuned for reasoning

Dumpling Mistral Nemo 8B i1 is a 8.43‑billion‑parameter model based on the Mistral architecture. It was trained with a context length of 1,024,000 tokens and fine‑tuned on multiple DPO datasets. The model is released under the apache‑2.0 license.

Good at

  • Reasoning
  • Fine‑tuned DPO performance
  • LLM inference with GGUF

Limits

  • No vision support
  • Requires at least 8 k context for memory estimates
  • Large VRAM needed for higher‑quality quants

Best for

  • Chatbot reasoning tasks
  • Custom fine‑tuning on small datasets
  • Local inference with limited VRAM

Who it’s for. Developers and researchers who need a reasoning‑focused Mistral model and can run GGUF files locally. The model is suitable for those who prefer open‑source licensing and have access to GPUs with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.2 GB 3.6 GB
Fits Get file →
IQ1_M2.3 GB 3.7 GB
Fits Get file →
IQ2_XXS2.6 GB 3.9 GB
Fits Get file →
IQ2_XS2.8 GB 4.2 GB
Fits Get file →
IQ2_S3.0 GB 4.3 GB
Fits Get file →
IQ2_M3.1 GB 4.5 GB
Fits Get file →
Q2_K_S3.2 GB 4.6 GB
Fits Get file →
Q2_K3.4 GB 4.8 GB
Fits Get file →
IQ3_XXS3.5 GB 4.9 GB
Fits Get file →
IQ3_XS3.7 GB 5.1 GB
Fits Get file →
Q3_K_S3.9 GB 5.3 GB
Fits Get file →
IQ3_S3.9 GB 5.3 GB
Fits Get file →
IQ3_M4.0 GB 5.4 GB
Fits Get file →
Q3_K_M4.2 GB 5.6 GB
Fits Get file →
Q3_K_L4.6 GB 5.9 GB
Fits Get file →
IQ4_XS4.7 GB 6.1 GB
Fits Get file →
Q4_04.9 GB 6.3 GB
Fits Get file →
IQ4_NL4.9 GB 6.3 GB
Fits Get file →
Q4_K_S5.0 GB 6.3 GB
Fits Get file →
Q4_K_M5.2 GB 6.6 GB
Fits Get file →
Q4_15.4 GB 6.8 GB
Fits Get file →
Q5_K_S5.9 GB 7.3 GB
Tight Get file →
Q5_K_M6.0 GB 7.4 GB
Tight Get file →
Q6_K6.9 GB 8.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.19 GB, 3.6 GB memory) or IQ1_M (2.33 GB, 3.7 GB memory). If you have 12 GB VRAM, Q4_K_M (5.19 GB, 6.6 GB memory) offers a good balance of size and quality. Larger models like Q6_K (6.92 GB, 8.3 GB memory) require 16 GB or more VRAM.

What GPU do you need for Dumpling Mistral Nemo 8B i1?

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 IQ2_XXS (2.6 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_L (4.6 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.0 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.9 GB file, about 8.3 GB in use).

Which Dumpling Mistral Nemo 8B i1 quant should you choose?

Q4_K_M is the usual starting point for Dumpling Mistral Nemo 8B i1: it balances file size and quality well. Here it is a 5.2 GB file.

If memory is tight, the smallest file is IQ1_S at 2.2 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

Architecturellama
Parameters8.43B
Layers26
Trained context1,024,000 tokens
KV cache (fp16)104 KB per token

Source

Quantized bymradermacher
FamilyMistral
Licenseapache-2.0
Downloads (HF)506
Last updated2025-02-12

Frequently asked questions about Dumpling Mistral Nemo 8B i1

How much VRAM does Dumpling Mistral Nemo 8B i1 need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.2 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 Dumpling Mistral Nemo 8B i1 on an 8 GB GPU?

Yes, with Q5_K_M: the 6.0 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Dumpling Mistral Nemo 8B i1 GGUF?

It depends on the quant: IQ1_S is 2.2 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.6 GB, IQ2_XS is 2.8 GB, IQ2_S is 3.0 GB, IQ2_M is 3.1 GB and 18 more.

What context length does Dumpling Mistral Nemo 8B i1 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.

Where can I download Dumpling Mistral Nemo 8B i1 GGUF?

The files are on Hugging Face in the mradermacher/Dumpling-Mistral-Nemo-8B-i1-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 Dumpling Mistral Nemo 8B i1 use?

Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quants, which fit within 8 GB VRAM and use about 3.6–3.7 GB memory at 8 k context.

Does the model support vision tasks?

No, the model has no vision capabilities and is text‑only.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Dumpling-Mistral-Nemo-8B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other small models

All small models →