SM

Smart-Lemon-Cookie-7B

SmartGGUF by backyardaiUpdated 2024-05-22
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

Smart-Lemon-Cookie-7B needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 22 quants, from 1.6 GB (IQ1_S) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Smart‑Lemon‑Cookie‑7B – a 7.24B‑parameter roleplay model in GGUF format

Smart‑Lemon‑Cookie‑7B is a 7.24B‑parameter llama‑based model merged with TIES using MTSAIR/multi_verse_model as a base. It supports a 32768‑token context and is designed for uncensored roleplay and storywriting. The model is available in multiple GGUF quantizations for varied hardware.

Good at

  • Roleplay with strong context following
  • Storywriting with detailed narratives
  • Reasoning across long contexts

Limits

  • No vision support
  • License not specified
  • Requires at least 3.2 GB VRAM for IQ1_S at 8k context

Best for

  • Local chat applications
  • Custom character creation
  • Lorebook integration

Who it’s for. Users who need a local, uncensored roleplay model that can handle long conversations and detailed storytelling. It is suitable for developers and hobbyists using llama.cpp or Backyard AI.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 3.2 GB
Fits Get file →
IQ2_XXS2.0 GB 3.6 GB
Fits Get file →
IQ2_XS2.2 GB 3.8 GB
Fits Get file →
IQ2_S2.3 GB 3.9 GB
Fits Get file →
IQ2_M2.5 GB 4.1 GB
Fits Get file →
Q2_K_S2.5 GB 4.1 GB
Fits Get file →
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XXS2.8 GB 4.4 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
IQ4_XS3.9 GB 5.5 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →
F1614.5 GB 16.1 GB
Too big Get file →

For 8 GB VRAM, IQ2_S (2.31 GB file, 3.9 GB memory) or Q2_K (2.72 GB file, 4.3 GB memory) are suitable. If 12 GB VRAM is available, Q3_K_M (3.52 GB file, 5.1 GB memory) offers higher quality. For maximum quality on 16 GB VRAM, Q5_K_M (5.13 GB file, 6.7 GB memory) or Q6_K (5.94 GB file, 7.5 GB memory) can be used.

What GPU do you need for Smart-Lemon-Cookie-7B?

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 IQ2_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).

Which Smart-Lemon-Cookie-7B quant should you choose?

Q4_K_M is the usual starting point for Smart-Lemon-Cookie-7B: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 1.6 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybackyardai
FamilySmart
Downloads (HF)1,061
Last updated2024-05-22

Frequently asked questions about Smart-Lemon-Cookie-7B

How much VRAM does Smart-Lemon-Cookie-7B need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 Smart-Lemon-Cookie-7B on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Smart-Lemon-Cookie-7B GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB, Q2_K_S is 2.5 GB and 16 more.

What context length does Smart-Lemon-Cookie-7B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Smart-Lemon-Cookie-7B GGUF?

The files are on Hugging Face in the backyardai/Smart-Lemon-Cookie-7B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Smart‑Lemon‑Cookie‑7B on 8 GB VRAM?

Yes, use IQ2_S or Q2_K quantizations which require approximately 3.9 GB or 4.3 GB VRAM at 8k context.

Does the model support vision tasks?

No, Smart‑Lemon‑Cookie‑7B does not include vision capabilities.

What is the maximum context length?

The model supports up to 32768 tokens of context.

Other GGUFs of Smart-Lemon-Cookie-7B

Similar models

Browse all →

More from backyardai

All by backyardai →

More Smart models

All Smart →

Other small models

All small models →