LL

Llama SmolTalk 3.2 1B Instruct i1

LlamaGGUF by mradermacherUpdated 2024-11-25
Download on Hugging Face
Parameters1.24B
Context128K
Layers16
Architecturellama
Smallest quant0.4 GB
Quick answer

Llama SmolTalk 3.2 1B Instruct i1 needs about 1.6 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.4 GB (IQ1_S) to 1.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

Llama SmolTalk 3.2 1B Instruct i1 – lightweight instruction‑tuned LLM

Llama SmolTalk 3.2 1B Instruct i1 is a 1.24B parameter model tuned for instruction following. It supports 131072 context tokens and is optimized for efficient text generation. The model is available in multiple GGUF quantizations for varied memory budgets.

Good at

  • Instruction following
  • Conversational dialogue
  • Content generation

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • CreativeML‑OpenRail‑M license

Best for

  • Chatbots on low‑resource devices
  • Rapid prototyping of instruction‑based apps
  • Generating concise summaries

Who it’s for. Developers building lightweight conversational agents or content generators who need a small, instruction‑tuned model. The model is suitable for projects that require efficient inference on modest hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.4 GB 1.2 GB
Fits Get file →
IQ1_M0.4 GB 1.2 GB
Fits Get file →
IQ2_XXS0.4 GB 1.2 GB
Fits Get file →
IQ2_XS0.5 GB 1.2 GB
Fits Get file →
IQ2_S0.5 GB 1.3 GB
Fits Get file →
IQ2_M0.5 GB 1.3 GB
Fits Get file →
IQ3_XXS0.6 GB 1.3 GB
Fits Get file →
Q2_K0.6 GB 1.3 GB
Fits Get file →
IQ3_XS0.6 GB 1.4 GB
Fits Get file →
Q3_K_S0.6 GB 1.4 GB
Fits Get file →
IQ3_S0.6 GB 1.4 GB
Fits Get file →
IQ3_M0.7 GB 1.4 GB
Fits Get file →
Q3_K_M0.7 GB 1.5 GB
Fits Get file →
Q3_K_L0.7 GB 1.5 GB
Fits Get file →
IQ4_XS0.7 GB 1.5 GB
Fits Get file →
Q4_00.8 GB 1.5 GB
Fits Get file →
Q4_00.8 GB 1.5 GB
Fits Get file →
Q4_00.8 GB 1.5 GB
Fits Get file →
Q4_00.8 GB 1.5 GB
Fits Get file →
Q4_K_S0.8 GB 1.5 GB
Fits Get file →
Q4_K_M0.8 GB 1.6 GB
Fits Get file →
Q5_K_S0.9 GB 1.7 GB
Fits Get file →
Q5_K_M0.9 GB 1.7 GB
Fits Get file →
Q6_K1.0 GB 1.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 (0.77 GB file, ~1.5 GB memory at 8k context). For 4 GB VRAM, choose IQ1_S (0.39 GB file, ~1.2 GB memory). For 2 GB VRAM, IQ2_XXS (0.45 GB file, ~1.2 GB memory) is the smallest option.

What GPU do you need for Llama SmolTalk 3.2 1B Instruct 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: the best quant that fits is Q6_K (1.0 GB file, about 1.8 GB in use).

Which Llama SmolTalk 3.2 1B Instruct i1 quant should you choose?

Q4_K_M is the usual starting point for Llama SmolTalk 3.2 1B Instruct i1: it balances file size and quality well. Here it is a 0.8 GB file.

If memory is tight, the smallest file is IQ1_S at 0.4 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
Parameters1.24B
Layers16
Trained context131,072 tokens
KV cache (fp16)32 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)800
Last updated2024-11-25

Frequently asked questions about Llama SmolTalk 3.2 1B Instruct i1

How much VRAM does Llama SmolTalk 3.2 1B Instruct i1 need?

About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.8 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 Llama SmolTalk 3.2 1B Instruct i1 on an 8 GB GPU?

Yes, with Q6_K: the 1.0 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama SmolTalk 3.2 1B Instruct i1 GGUF?

It depends on the quant: IQ1_S is 0.4 GB, IQ1_M is 0.4 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.5 GB, IQ2_S is 0.5 GB, IQ2_M is 0.5 GB and 18 more.

What context length does Llama SmolTalk 3.2 1B Instruct i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download Llama SmolTalk 3.2 1B Instruct i1 GGUF?

The files are on Hugging Face in the mradermacher/Llama-SmolTalk-3.2-1B-Instruct-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 Llama SmolTalk 3.2 1B Instruct i1 use?

Hugging Face lists the license as creativeml-openrail-m. 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, the Q4_0 quantization requires about 1.5 GB VRAM at 8k context, which fits within 8 GB.

Does the model support image inputs?

No, the model has no vision capabilities and only processes text.

What license applies to this model?

The model is released under the creativeml-openrail-m license.

Other GGUFs of Llama-SmolTalk-3.2-1B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other tiny models

All tiny models →