ST

stablelm tuned alpha 7b i1

StablelmGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters7.87B
Context4K
Layers16
Architecturegptneox
Smallest quant1.8 GB
Quick answer

stablelm tuned alpha 7b i1 needs about 8.8 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 1.8 GB (IQ1_S) to 6.5 GB (Q6_K).

StableLM-Tuned-Alpha 7B, fine‑tuned decoder‑only language model

StableLM‑Tuned‑Alpha 7B is a 7.87 billion‑parameter decoder‑only model based on the NeoX architecture. It is fine‑tuned on instruction‑following datasets and released under a CC BY‑NC‑SA‑4.0 license. The model supports up to 4096 context tokens.

Good at

  • Instruction following
  • Chat‑style dialogue
  • English text generation

Limits

  • No vision support
  • CC BY‑NC‑SA‑4.0 license limits commercial use
  • Requires 4096‑token context

Best for

  • Building chatbots
  • Generating instructional content
  • Creating conversational agents

Who it’s for. Developers building open‑source chat applications or research projects that require a large language model with instruction‑following capabilities. The model is suitable for non‑commercial use under the CC BY‑NC‑SA‑4.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.8 GB 3.9 GB
Fits Get file →
IQ1_M2.0 GB 4.1 GB
Fits Get file →
IQ2_XXS2.2 GB 4.3 GB
Fits Get file →
IQ2_XS2.4 GB 4.5 GB
Fits Get file →
IQ2_S2.6 GB 4.7 GB
Fits Get file →
IQ2_M2.8 GB 4.9 GB
Fits Get file →
Q2_K3.0 GB 5.2 GB
Fits Get file →
IQ3_XXS3.2 GB 5.3 GB
Fits Get file →
IQ3_XS3.4 GB 5.5 GB
Fits Get file →
IQ3_S3.5 GB 5.6 GB
Fits Get file →
Q3_K_S3.5 GB 5.6 GB
Fits Get file →
IQ3_M3.9 GB 6.0 GB
Fits Get file →
Q3_K_M4.2 GB 6.3 GB
Fits Get file →
IQ4_XS4.3 GB 6.4 GB
Fits Get file →
Q3_K_L4.5 GB 6.6 GB
Fits Get file →
Q4_04.5 GB 6.6 GB
Fits Get file →
Q4_K_S4.6 GB 6.7 GB
Fits Get file →
Q4_K_M5.1 GB 7.2 GB
Fits Get file →
Q5_K_S5.5 GB 7.6 GB
Tight Get file →
Q5_K_M5.9 GB 8.0 GB
Tight Get file →
Q6_K6.5 GB 8.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.82 GB, 5.5 GB memory) or IQ1_M (1.96 GB, 5.7 GB). For 12 GB VRAM, IQ2_S (2.58 GB, 6.3 GB) or Q2_K (3.05 GB, 6.8 GB) are good choices. Larger VRAM allows higher‑quality quants such as Q5_K_M (5.86 GB, 9.6 GB).

What GPU do you need for stablelm tuned alpha 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: the best quant that fits is IQ2_XXS (2.2 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ4_XS (4.3 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.5 GB file, about 10.2 GB in use).

Which stablelm tuned alpha 7b i1 quant should you choose?

Q4_K_M is the usual starting point for stablelm tuned alpha 7b i1: it balances file size and quality well. Here it is a 5.1 GB file.

If memory is tight, the smallest file is IQ1_S at 1.8 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

Architecturegptneox
Parameters7.87B
Layers16
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
FamilyStablelm
Downloads (HF)3,556
Last updated2024-08-02

Frequently asked questions about stablelm tuned alpha 7b i1

How much VRAM does stablelm tuned alpha 7b i1 need?

About 8.8 GB at Q4_K_M with an 8K context window. That is the 5.1 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 tuned alpha 7b i1 on an 8 GB GPU?

Yes, with IQ4_XS: the 4.3 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 stablelm tuned alpha 7b i1 GGUF?

It depends on the quant: IQ1_S is 1.8 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.2 GB, IQ2_XS is 2.4 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 15 more.

What context length does stablelm tuned alpha 7b i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download stablelm tuned alpha 7b i1 GGUF?

The files are on Hugging Face in the mradermacher/stablelm-tuned-alpha-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 stablelm tuned alpha 7b i1 use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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, using IQ1_S or IQ1_M quants will fit within 8 GB VRAM with approximate 5.5–5.7 GB memory usage.

What license does the model use?

The model is licensed under CC BY‑NC‑SA‑4.0, which allows non‑commercial use with attribution.

Does the model support vision tasks?

No, the model is a text‑only decoder‑only language model and does not support vision inputs.

Other GGUFs of stablelm-tuned-alpha-7b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Stablelm models

All Stablelm →

Other small models

All small models →