BI

Bigstral 12b 32k

BigstralGGUF by mradermacherUpdated 2024-09-11
Download on Hugging Face
Parameters12.5B
Context32K
Layers56
Architecturellama
Smallest quant2.7 GB
Quick answer

Bigstral 12b 32k needs about 9.9 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.7 GB (IQ1_S) to 10.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Bigstral 12b 32k – 12.5B parameter Llama model with 32k context

Bigstral 12b 32k is a 12.5B parameter Llama‑style model trained on 32k token context. It is available in multiple GGUF quantizations from IQ1_S to Q6_K. The model is released under the apache‑2.0 license.

Good at

  • Large context handling
  • High token capacity
  • LLM instruction following

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is apache‑2.0

Best for

  • Chatbots needing long context
  • Code generation with long prompts
  • Research on large‑context LLMs

Who it’s for. Developers and researchers who need a 12B Llama model with 32k context and can run GGUF files. The model is suitable for local deployment using llama.cpp or similar engines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.7 GB 5.1 GB
Fits Get file →
IQ1_M3.0 GB 5.3 GB
Fits Get file →
IQ2_XXS3.4 GB 5.8 GB
Fits Get file →
IQ2_XS3.7 GB 6.1 GB
Fits Get file →
IQ2_S3.9 GB 6.3 GB
Fits Get file →
IQ2_M4.3 GB 6.6 GB
Fits Get file →
Q2_K4.6 GB 7.0 GB
Fits Get file →
IQ3_XXS4.8 GB 7.2 GB
Tight Get file →
IQ3_XS5.2 GB 7.5 GB
Tight Get file →
Q3_K_S5.4 GB 7.8 GB
Tight Get file →
IQ3_S5.4 GB 7.8 GB
Tight Get file →
IQ3_M5.6 GB 8.0 GB
Too big Get file →
Q3_K_M6.0 GB 8.4 GB
Too big Get file →
Q3_K_L6.6 GB 8.9 GB
Too big Get file →
IQ4_XS6.7 GB 9.1 GB
Too big Get file →
Q4_07.1 GB 9.4 GB
Too big Get file →
Q4_07.1 GB 9.4 GB
Too big Get file →
Q4_07.1 GB 9.4 GB
Too big Get file →
Q4_07.1 GB 9.5 GB
Too big Get file →
Q4_K_S7.1 GB 9.5 GB
Too big Get file →
Q4_K_M7.5 GB 9.9 GB
Too big Get file →
Q5_K_S8.6 GB 11.0 GB
Too big Get file →
Q5_K_M8.8 GB 11.2 GB
Too big Get file →
Q6_K10.2 GB 12.6 GB
Too big Get file →

For 8 GB VRAM, use IQ2_S (file size 3.93 GB, estimated 6.3 GB memory). For 12 GB VRAM, Q4_K_M (file size 7.51 GB, estimated 9.9 GB memory) or Q5_K_S (file size 8.6 GB, estimated 11 GB memory). For 16 GB VRAM, Q6_K (file size 10.24 GB, estimated 12.6 GB memory).

What GPU do you need for Bigstral 12b 32k?

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 IQ2_XXS (3.4 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_M (5.6 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (8.8 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.2 GB file, about 12.6 GB in use).

Which Bigstral 12b 32k quant should you choose?

Q4_K_M is the usual starting point for Bigstral 12b 32k: it balances file size and quality well. Here it is a 7.5 GB file.

If memory is tight, the smallest file is IQ1_S at 2.7 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
Parameters12.5B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized bymradermacher
FamilyBigstral
Licenseapache-2.0
Downloads (HF)2,151
Last updated2024-09-11

Frequently asked questions about Bigstral 12b 32k

How much VRAM does Bigstral 12b 32k need?

About 9.9 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Bigstral 12b 32k on an 8 GB GPU?

Yes, with IQ3_M: the 5.6 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 Bigstral 12b 32k GGUF?

It depends on the quant: IQ1_S is 2.7 GB, IQ1_M is 3.0 GB, IQ2_XXS is 3.4 GB, IQ2_XS is 3.7 GB, IQ2_S is 3.9 GB, IQ2_M is 4.3 GB and 18 more.

What context length does Bigstral 12b 32k support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Bigstral 12b 32k GGUF?

The files are on Hugging Face in the mradermacher/bigstral-12b-32k-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 Bigstral 12b 32k 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 Bigstral 12b 32k on 8 GB VRAM?

Use the IQ2_S quant, which requires about 6.3 GB memory at 8k context. It fits within 8 GB VRAM with headroom.

Does this model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of bigstral-12b-32k

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bigstral models

All Bigstral →

Other medium models

All medium models →