BL

Bloom 7b1

BloomGGUF by mradermacherUpdated 2025-03-08
Download on Hugging Face
Parameters8.1B
Context4K
Layers30
Architecturebloom
Smallest quant2.3 GB
Quick answer

Bloom 7b1 needs about 9.8 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.3 GB (IQ1_S) to 6.7 GB (Q6_K).

Bloom 7b1 – 8.1B parameter language model, quantized for GGUF use

Bloom 7b1 is a transformer‑based language model with 8.1B parameters. It supports a 4096 token context window and is trained on multilingual data. The model is available in multiple GGUF quantizations for efficient inference.

Good at

  • Coding assistance
  • Text generation
  • Multilingual support

Limits

  • No vision capabilities
  • License: bigscience-bloom-rail-1.0
  • Requires GPU for best performance

Best for

  • Developers needing a lightweight coding assistant
  • Researchers testing multilingual language models
  • Embedded systems with limited VRAM

Who it’s for. Engineers and researchers who need a large language model that can be run locally with GGUF quantizations. The model is suitable for environments where GPU memory is constrained but coding and text generation tasks are required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.3 GB 4.8 GB
Fits Get file →
IQ1_M2.4 GB 4.9 GB
Fits Get file →
IQ2_XXS2.6 GB 5.1 GB
Fits Get file →
IQ2_XS2.8 GB 5.3 GB
Fits Get file →
IQ2_S3.0 GB 5.5 GB
Fits Get file →
IQ2_M3.2 GB 5.7 GB
Fits Get file →
Q2_K_S3.2 GB 5.7 GB
Fits Get file →
Q2_K3.4 GB 5.9 GB
Fits Get file →
IQ3_XXS3.5 GB 6.0 GB
Fits Get file →
IQ3_XS3.8 GB 6.3 GB
Fits Get file →
IQ3_S3.9 GB 6.4 GB
Fits Get file →
Q3_K_S3.9 GB 6.4 GB
Fits Get file →
IQ3_M4.2 GB 6.7 GB
Fits Get file →
Q3_K_M4.4 GB 7.0 GB
Fits Get file →
IQ4_XS4.6 GB 7.1 GB
Fits Get file →
Q3_K_L4.7 GB 7.3 GB
Tight Get file →
IQ4_NL4.8 GB 7.4 GB
Tight Get file →
Q4_04.9 GB 7.4 GB
Tight Get file →
Q4_K_S4.9 GB 7.4 GB
Tight Get file →
Q4_K_M5.3 GB 7.8 GB
Tight Get file →
Q4_15.3 GB 7.8 GB
Tight Get file →
Q5_K_S5.7 GB 8.2 GB
Too big Get file →
Q5_K_M6.0 GB 8.6 GB
Too big Get file →
Q6_K6.7 GB 9.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.3 GB, 6.8 GB memory) or IQ1_M (2.43 GB, 7 GB memory). If 12 GB VRAM is available, Q2_K (3.44 GB, 8 GB memory) or Q3_K (3.9 GB, 8.4 GB memory) provide higher quality. Larger VRAM allows use of Q4_K_M (5.27 GB, 9.8 GB memory) or Q5_K_M (6.05 GB, 10.6 GB memory).

What GPU do you need for Bloom 7b1?

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_XXS (3.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 11.2 GB in use).

Which Bloom 7b1 quant should you choose?

Q4_K_M is the usual starting point for Bloom 7b1: it balances file size and quality well. Here it is a 5.3 GB file.

If memory is tight, the smallest file is IQ1_S at 2.3 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

Architecturebloom
Parameters8.1B
Layers30
Trained context4,096 tokens
KV cache (fp16)480 KB per token

Source

Quantized bymradermacher
FamilyBloom
Downloads (HF)674
Last updated2025-03-08

Frequently asked questions about Bloom 7b1

How much VRAM does Bloom 7b1 need?

About 9.8 GB at Q4_K_M with an 8K context window. That is the 5.3 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 Bloom 7b1 on an 8 GB GPU?

Yes, with IQ3_XXS: the 3.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bloom 7b1 GGUF?

It depends on the quant: IQ1_S is 2.3 GB, IQ1_M is 2.4 GB, IQ2_XXS is 2.6 GB, IQ2_XS is 2.8 GB, IQ2_S is 3.0 GB, IQ2_M is 3.2 GB and 18 more.

What context length does Bloom 7b1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.0 GB at 8K and 2.0 GB at 4K.

Where can I download Bloom 7b1 GGUF?

The files are on Hugging Face in the mradermacher/bloom-7b1-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 Bloom 7b1 use?

Hugging Face lists the license as bigscience-bloom-rail-1.0. 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 Bloom 7b1 on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations, which fit within 8 GB VRAM and require about 6.8–7 GB memory at 8k context.

Does Bloom 7b1 support vision tasks?

No, Bloom 7b1 is a text‑only language model and has no vision capabilities.

What license applies to Bloom 7b1?

The model is released under the bigscience-bloom-rail-1.0 license.

Other GGUFs of bloom-7b1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bloom models

All Bloom →

Other small models

All small models →