ST

StableLM 2 1.6B Chat

StablelmGGUF by mradermacherUpdated 2024-12-13
Download on Hugging Face
Parameters1.64B
Context4K
Layers24
Architecturestablelm
Smallest quant0.5 GB
Quick answer

StableLM 2 1.6B Chat needs about 3.1 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.5 GB (IQ1_S) to 1.4 GB (Q6_K).

StableLM 2 1.6B Chat – instruction‑tuned LLM in GGUF format

StableLM 2 1.6B Chat is a 1.6 billion parameter transformer decoder model. It is instruction tuned with Direct Preference Optimization and supports ChatML format. The model is available in multiple GGUF quantizations.

Good at

  • Chat‑style interactions
  • Tool‑use instructions
  • English language generation

Limits

  • No vision support
  • Requires safety guardrails
  • License is non‑commercial

Best for

  • Building chatbots
  • Generating tool‑aware responses
  • Prototyping instruction‑tuned models

Who it’s for. Developers building chat‑like applications who need a lightweight, instruction‑tuned model. The model is suitable for research and non‑commercial use; commercial deployment requires contacting Stability AI.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.5 GB 1.8 GB
Fits Get file →
IQ1_M0.5 GB 1.8 GB
Fits Get file →
IQ2_XXS0.5 GB 1.8 GB
Fits Get file →
IQ2_XS0.6 GB 1.9 GB
Fits Get file →
IQ2_S0.6 GB 1.9 GB
Fits Get file →
Q2_K_S0.7 GB 2.0 GB
Fits Get file →
IQ2_M0.7 GB 2.0 GB
Fits Get file →
Q2_K0.7 GB 2.0 GB
Fits Get file →
IQ3_XXS0.7 GB 2.0 GB
Fits Get file →
IQ3_XS0.8 GB 2.1 GB
Fits Get file →
IQ3_S0.8 GB 2.1 GB
Fits Get file →
Q3_K_S0.8 GB 2.1 GB
Fits Get file →
IQ3_M0.8 GB 2.1 GB
Fits Get file →
Q3_K_M0.9 GB 2.2 GB
Fits Get file →
Q3_K_L0.9 GB 2.2 GB
Fits Get file →
IQ4_XS0.9 GB 2.2 GB
Fits Get file →
Q4_01.0 GB 2.3 GB
Fits Get file →
Q4_K_S1.0 GB 2.3 GB
Fits Get file →
Q4_K_M1.0 GB 2.3 GB
Fits Get file →
Q5_K_S1.2 GB 2.5 GB
Fits Get file →
Q5_K_M1.2 GB 2.5 GB
Fits Get file →
Q6_K1.4 GB 2.7 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (file size 0.48 GB or 0.5 GB, memory ~2.6 GB). For 12 GB VRAM, IQ2_S or Q2_K_S (0.62 GB or 0.99 GB, memory ~2.7 GB). For 16 GB VRAM, Q4_K_M or Q5_K_S (1.03 GB or 1.16 GB, memory ~3.1 GB).

What GPU do you need for StableLM 2 1.6B Chat?

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 Q6_K (1.4 GB file, about 3.5 GB in use).

Which StableLM 2 1.6B Chat quant should you choose?

Q4_K_M is the usual starting point for StableLM 2 1.6B Chat: it balances file size and quality well. Here it is a 1.0 GB file.

If memory is tight, the smallest file is IQ1_S at 0.5 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

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

Source

Quantized bymradermacher
FamilyStablelm
Licenseother
Downloads (HF)744
Last updated2024-12-13

Frequently asked questions about StableLM 2 1.6B Chat

How much VRAM does StableLM 2 1.6B Chat need?

About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.0 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 1.6B Chat on an 8 GB GPU?

Yes, with Q6_K: the 1.4 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of StableLM 2 1.6B Chat GGUF?

It depends on the quant: IQ1_S is 0.5 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB, Q2_K_S is 0.7 GB and 16 more.

What context length does StableLM 2 1.6B Chat 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 1.6B Chat GGUF?

The files are on Hugging Face in the mradermacher/stablelm-2-1_6b-chat-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 StableLM 2 1.6B Chat 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 1.6B Chat on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations which use about 2.6 GB of VRAM at 8 k context.

Does the model support image inputs?

No, the model has no vision capability.

Is the model free for commercial use?

No, the license is non‑commercial; contact Stability AI for commercial terms.

Other GGUFs of stablelm-2-1_6b-chat

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Stablelm models

All Stablelm →

Other tiny models

All tiny models →