IN

INTELLECT 1

IntellectGGUF by mradermacherUpdated 2025-03-31
Download on Hugging Face
Parameters10.2B
Context8K
Layers42
Architecturellama
Smallest quant2.5 GB
Quick answer

INTELLECT 1 needs about 8.1 GB of memory at Q4_K_M (a 6.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.5 GB (IQ1_S) to 8.4 GB (Q6_K).

INTELLECT 1 – a 10.2B parameter llama model

INTELLECT 1 is a 10.2 billion parameter language model trained from scratch on 1 trillion tokens of English text and code. It uses the llama architecture and supports a context length of 8192 tokens. The model is released under the Apache 2.0 license.

Good at

  • Large context text generation
  • Code understanding
  • Multilingual text handling

Limits

  • No vision support
  • Requires BOS token at start
  • No instruction tuning in base model

Best for

  • Local inference on high‑VRAM GPUs
  • Research prototyping
  • Fine‑tuning for specialized domains

Who it’s for. Researchers and developers who need a large, open‑source language model for local deployment. The model is suitable for those who can provide the necessary compute resources and are comfortable working with GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.5 GB 4.4 GB
Fits Get file →
IQ1_M2.7 GB 4.6 GB
Fits Get file →
IQ2_XXS3.0 GB 4.9 GB
Fits Get file →
IQ2_XS3.3 GB 5.2 GB
Fits Get file →
IQ2_S3.4 GB 5.3 GB
Fits Get file →
IQ2_M3.7 GB 5.6 GB
Fits Get file →
Q2_K_S3.7 GB 5.6 GB
Fits Get file →
Q2_K4.0 GB 5.9 GB
Fits Get file →
IQ3_XXS4.1 GB 6.0 GB
Fits Get file →
IQ3_XS4.4 GB 6.3 GB
Fits Get file →
Q3_K_S4.6 GB 6.5 GB
Fits Get file →
IQ3_S4.6 GB 6.5 GB
Fits Get file →
IQ3_M4.8 GB 6.7 GB
Fits Get file →
Q3_K_M5.1 GB 7.0 GB
Fits Get file →
Q3_K_L5.5 GB 7.4 GB
Tight Get file →
IQ4_XS5.6 GB 7.5 GB
Tight Get file →
Q4_05.9 GB 7.8 GB
Tight Get file →
IQ4_NL5.9 GB 7.8 GB
Tight Get file →
Q4_K_S5.9 GB 7.8 GB
Tight Get file →
Q4_K_M6.2 GB 8.1 GB
Too big Get file →
Q4_16.5 GB 8.4 GB
Too big Get file →
Q5_K_S7.1 GB 9.0 GB
Too big Get file →
Q5_K_M7.3 GB 9.2 GB
Too big Get file →
Q6_K8.4 GB 10.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.48 GB, estimated 4.4 GB memory). For 12 GB VRAM, IQ2_M (3.68 GB, 5.6 GB memory) or Q2_K (3.98 GB, 5.9 GB memory). For 16 GB VRAM, Q3_K_M (5.06 GB, 7 GB memory) or Q4_K_M (6.23 GB, 8.1 GB memory).

What GPU do you need for INTELLECT 1?

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: the best quant that fits is IQ3_XXS (4.1 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_S (5.9 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.4 GB file, about 10.3 GB in use).

Which INTELLECT 1 quant should you choose?

Q4_K_M is the usual starting point for INTELLECT 1: it balances file size and quality well. Here it is a 6.2 GB file.

If memory is tight, the smallest file is IQ1_S at 2.5 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

Architecturellama
Parameters10.2B
Layers42
Trained context8,192 tokens
KV cache (fp16)168 KB per token

Source

Quantized bymradermacher
FamilyIntellect
Licenseapache-2.0
Downloads (HF)1,548
Last updated2025-03-31

Frequently asked questions about INTELLECT 1

How much VRAM does INTELLECT 1 need?

About 8.1 GB at Q4_K_M with an 8K context window. That is the 6.2 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 INTELLECT 1 on an 8 GB GPU?

Yes, with Q4_K_S: the 5.9 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of INTELLECT 1 GGUF?

It depends on the quant: IQ1_S is 2.5 GB, IQ1_M is 2.7 GB, IQ2_XXS is 3.0 GB, IQ2_XS is 3.3 GB, IQ2_S is 3.4 GB, IQ2_M is 3.7 GB and 18 more.

What context length does INTELLECT 1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.4 GB at 8K and 1.4 GB at 8K.

Where can I download INTELLECT 1 GGUF?

The files are on Hugging Face in the mradermacher/INTELLECT-1-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 INTELLECT 1 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 INTELLECT 1 on 8 GB VRAM?

Yes, the IQ1_S quant requires about 4.4 GB memory at 8k context, which fits in 8 GB VRAM with headroom.

Does INTELLECT 1 support vision tasks?

No, the base model does not include vision capabilities.

Do I need to add a BOS token when generating text?

Yes, a BOS token must be added at the start of each sample; otherwise performance may be impacted.

Other GGUFs of INTELLECT-1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Intellect models

All Intellect →

Other medium models

All medium models →