MP

mpt 7b i1

MptGGUF by mradermacherUpdated 2024-09-10
Download on Hugging Face
Parameters6.65B
Context2K
Layers32
Architecturempt
Smallest quant1.5 GB
Quick answer

mpt 7b i1 needs about 9.1 GB of memory at Q4_K_M (a 4.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 1.5 GB (IQ1_S) to 5.5 GB (Q6_K).

MPT 7B i1 – a 6.65B parameter GGUF model

MPT 7B i1 is a 6.65 billion parameter language model based on mosaicml/mpt-7b. It is available in multiple quantizations for use with llama.cpp. The model supports a 2048 token context window and is released under the Apache‑2.0 license.

Good at

  • Efficient inference on modest GPUs
  • Low‑memory quantizations
  • Stable performance across quant types

Limits

  • No vision capabilities
  • Requires 8k context for memory estimates
  • No mixture‑of‑experts

Best for

  • Chatbots on 8‑GB VRAM
  • Local code generation
  • Quick prototyping with low‑latency

Who it’s for. Developers and researchers who need a compact, open‑source LLM for local deployment. The model is suitable for projects that require a small context window and moderate memory usage.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 3.0 GB
Fits Get file →
IQ1_M1.6 GB 3.2 GB
Fits Get file →
IQ2_XXS1.8 GB 3.4 GB
Fits Get file →
IQ2_XS2.0 GB 3.6 GB
Fits Get file →
IQ2_S2.1 GB 3.7 GB
Fits Get file →
IQ2_M2.3 GB 3.9 GB
Fits Get file →
Q2_K2.6 GB 4.1 GB
Fits Get file →
IQ3_XXS2.6 GB 4.2 GB
Fits Get file →
IQ3_XS2.9 GB 4.4 GB
Fits Get file →
IQ3_S2.9 GB 4.5 GB
Fits Get file →
Q3_K_S2.9 GB 4.5 GB
Fits Get file →
IQ3_M3.3 GB 4.8 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
IQ4_XS3.6 GB 5.2 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_K_S3.8 GB 5.4 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
Q4_K_M4.3 GB 5.8 GB
Fits Get file →
Q5_K_S4.6 GB 6.2 GB
Fits Get file →
Q5_K_M5.0 GB 6.5 GB
Fits Get file →
Q6_K5.5 GB 7.0 GB
Fits Get file →

For 8‑GB VRAM, use IQ1_S (6.3 GB) or IQ1_M (6.4 GB). If 12‑GB VRAM is available, IQ2_S (6.9 GB) or Q4_0 (8.6 GB) provide a balance of size and quality. For 16‑GB VRAM, Q5_K_M (9.8 GB) or Q6_K (10.3 GB) offer higher fidelity.

What GPU do you need for mpt 7b 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ3_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 10.3 GB in use).

Which mpt 7b i1 quant should you choose?

Q4_K_M is the usual starting point for mpt 7b i1: it balances file size and quality well. Here it is a 4.3 GB file.

If memory is tight, the smallest file is IQ1_S at 1.5 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

Architecturempt
Parameters6.65B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyMpt
Base modelmosaicml/mpt-7b
Licenseapache-2.0
Downloads (HF)2,638
Last updated2024-09-10

Frequently asked questions about mpt 7b i1

How much VRAM does mpt 7b i1 need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 4.3 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 mpt 7b i1 on an 8 GB GPU?

Yes, with IQ3_S: the 2.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mpt 7b i1 GGUF?

It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.6 GB, IQ2_XXS is 1.8 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.1 GB, IQ2_M is 2.3 GB and 15 more.

What context length does mpt 7b i1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download mpt 7b i1 GGUF?

The files are on Hugging Face in the mradermacher/mpt-7b-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 mpt 7b 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 quantizations, which require approximately 6.3–6.4 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the maximum context length?

The trained context length is 2048 tokens.

Other GGUFs of mpt-7b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mpt models

All Mpt →

Other small models

All small models →