ST

stablelm 2 zephyr 1 6b

StablelmGGUF by stabilityaiUpdated 2024-06-03
Download on Hugging Face
Parameters1.64B
Context4K
Layers24
Architecturestablelm
Smallest quant1.0 GB
Quick answer

stablelm 2 zephyr 1 6b needs about 3.3 GB of memory at Q5_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.0 GB (Q4_0) to 3.3 GB.

StableLM 2 Zephyr 1.6B – a 1.6 B parameter instruction‑tuned language model

StableLM 2 Zephyr 1.6B is a 1.6 billion parameter auto‑regressive model based on the transformer decoder architecture. It is instruction tuned with Direct Preference Optimization and trained on a mix of public and synthetic datasets. The model supports English and is available in several GGUF quantizations.

Good at

  • Instruction following
  • Chat‑style responses
  • Reasoning tasks

Limits

  • No vision support
  • License is non‑commercial research only
  • Context limited to 4096 tokens

Best for

  • Chatbot prototypes
  • Text generation demos
  • Educational tools

Who it’s for. Developers building chat interfaces or educational applications who need a lightweight, instruction‑tuned model. The model is suitable for research and non‑commercial use under the StabilityAI Non‑Commercial Research Community License.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.0 GB 2.3 GB
Fits Get file →
Q4_11.1 GB 2.4 GB
Fits Get file →
Q5_K_M1.2 GB 2.5 GB
Fits Get file →
Q8_01.8 GB 3.1 GB
Fits Get file →
—3.3 GB 4.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 (0.98 GB file, ~3.1 GB VRAM at 8 k context). For 12 GB VRAM, Q4_1 or Q5_K_M are suitable (1.07–1.19 GB file, ~3.2–3.3 GB VRAM). Larger VRAM allows Q8_0 (1.75 GB file, ~3.9 GB VRAM).

What GPU do you need for stablelm 2 zephyr 1 6b?

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 Q8_0 (1.8 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (3.3 GB file, about 5.4 GB in use).

Which stablelm 2 zephyr 1 6b quant should you choose?

Q5_K_M (1.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_0 at 1.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestablelm
Parameters1.64B
Layers24
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bystabilityai
FamilyStablelm
Licenseother
Downloads (HF)7,957
Last updated2024-06-03

Frequently asked questions about stablelm 2 zephyr 1 6b

How much VRAM does stablelm 2 zephyr 1 6b need?

About 3.3 GB at Q5_K_M with an 8K context window. That is the 1.2 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 stablelm 2 zephyr 1 6b on an 8 GB GPU?

Yes, with the smaller files: the 3.3 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of stablelm 2 zephyr 1 6b GGUF?

It depends on the quant: Q4_0 is 1.0 GB, Q4_1 is 1.1 GB, Q5_K_M is 1.2 GB, Q8_0 is 1.8 GB, file is 3.3 GB.

What context length does stablelm 2 zephyr 1 6b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download stablelm 2 zephyr 1 6b GGUF?

The files are on Hugging Face in the stabilityai/stablelm-2-zephyr-1_6b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does stablelm 2 zephyr 1 6b use?

Hugging Face lists the license as other. 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 StableLM 2 Zephyr 1.6B on 8 GB VRAM?

Yes, the Q4_0 quantization requires about 3.1 GB VRAM at 8 k context, which fits in 8 GB.

Is this model suitable for commercial products?

The license is non‑commercial research only; commercial use requires contacting Stability AI.

What is the maximum context length?

The model supports up to 4096 tokens of context.

Similar models

Browse all →

More from stabilityai

All by stabilityai →

More Stablelm models

All Stablelm →

Other tiny models

All tiny models →