LL

llm-compiler-7b-ftd

LlmGGUF by legraphistaUpdated 2024-06-28
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

llm-compiler-7b-ftd needs about 7.9 GB of memory at IQ3_M (a 3.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 1.5 GB (IQ1_S) to 13.5 GB.

llm-compiler-7b-ftd: 6.74B Llama model quantized with IMatrix

llm-compiler-7b-ftd is a 6.74B parameter Llama model from facebook/llm-compiler-7b-ftd. It has been quantized by legraphista using IMatrix and common quant schemes. The model supports a 16384 token context window.

Good at

  • Text generation
  • Fine‑tuned language tasks
  • Low‑latency inference

Limits

  • No vision support
  • License is other
  • Requires 8k context for estimates

Best for

  • Chatbots on modest GPUs
  • Rapid prototyping
  • Educational demos

Who it’s for. Developers and researchers who need a compact Llama model with IMatrix quantization. The model is suitable for local inference using llama.cpp on systems with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 6.3 GB
Fits Get file →
IQ1_M1.7 GB 6.4 GB
Fits Get file →
IQ2_XXS1.9 GB 6.6 GB
Fits Get file →
IQ2_XS2.0 GB 6.8 GB
Fits Get file →
IQ2_S2.2 GB 7.0 GB
Fits Get file →
Q2_K_S2.3 GB 7.1 GB
Fits Get file →
IQ2_M2.4 GB 7.2 GB
Fits Get file →
Q2_K2.5 GB 7.3 GB
Tight Get file →
IQ3_XXS2.6 GB 7.4 GB
Tight Get file →
IQ3_XS2.8 GB 7.6 GB
Tight Get file →
IQ3_S2.9 GB 7.7 GB
Tight Get file →
Q3_K_S2.9 GB 7.7 GB
Tight Get file →
IQ3_M3.1 GB 7.9 GB
Tight Get file →
Q3_K3.3 GB 8.1 GB
Too big Get file →
Q3_K_L3.6 GB 8.4 GB
Too big Get file →
IQ4_XS3.6 GB 8.4 GB
Too big Get file →
IQ4_NL3.8 GB 8.6 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K4.1 GB 8.9 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →
BF1613.5 GB 18.3 GB
Too big Get file →
—13.5 GB 18.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.53 GB file, 6.3 GB memory) or IQ1_M (1.65 GB file, 6.4 GB memory). For 12 GB VRAM, Q8_0 (7.16 GB file, 12 GB memory) is a good balance. Higher quants like Q5_K or Q6_K require 9.4–10.3 GB memory and larger files.

What GPU do you need for llm-compiler-7b-ftd?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (13.5 GB file, about 18.3 GB in use).

Which llm-compiler-7b-ftd quant should you choose?

IQ3_M (3.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 1.5 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

Architecturellama
Parameters6.74B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bylegraphista
FamilyLlm
Licenseother
Downloads (HF)1,810
Last updated2024-06-28

Frequently asked questions about llm-compiler-7b-ftd

How much VRAM does llm-compiler-7b-ftd need?

About 7.9 GB at IQ3_M with an 8K context window. That is the 3.1 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 llm-compiler-7b-ftd on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of llm-compiler-7b-ftd GGUF?

It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.2 GB, Q2_K_S is 2.3 GB and 19 more.

What context length does llm-compiler-7b-ftd support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download llm-compiler-7b-ftd GGUF?

The files are on Hugging Face in the legraphista/llm-compiler-7b-ftd-IMat-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 llm-compiler-7b-ftd 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 IQ1_S on 8 GB VRAM?

Yes, IQ1_S requires 6.3 GB memory at 8k context, which fits in 8 GB VRAM.

What is the largest quant I can use on 12 GB VRAM?

Q8_0 uses 12 GB memory at 8k context, matching a 12 GB VRAM system.

Does this model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of llm-compiler-7b-ftd

Similar models

Browse all →

More from legraphista

All by legraphista →

More Llm models

All Llm →

Other small models

All small models →