NE

neo_7b_instruct_v0.1

NeoGGUF by legraphistaUpdated 2024-05-31
Download on Hugging Face
Parameters7.79B
Context8K
Layers28
Architecturellama
Smallest quant1.7 GB
Quick answer

neo_7b_instruct_v0.1 needs about 6.8 GB of memory at IQ3_M (a 3.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 1.7 GB (IQ1_S) to 15.6 GB.

Neo 7B Instruct v0.1 – instruction‑tuned Llama‑style model

Neo 7B Instruct v0.1 is a 7.79 billion‑parameter Llama‑based model fine‑tuned for instruction following. It supports a 8192‑token context window and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations for llama.cpp inference.

Good at

  • Instruction following
  • Chat‑style interactions
  • Text generation

Limits

  • No vision support
  • Requires 8 k context for full capability
  • License is Apache‑2.0

Best for

  • Chatbots on edge devices
  • Rapid prototyping of instruction‑based apps
  • Local inference with limited GPU memory

Who it’s for. Developers and researchers who need an open‑source, instruction‑tuned Llama‑style model with a moderate parameter count. The model is suitable for local deployment and experimentation in environments with limited GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.7 GB 5.0 GB
Fits Get file →
IQ1_M1.9 GB 5.2 GB
Fits Get file →
IQ2_XXS2.1 GB 5.5 GB
Fits Get file →
IQ2_XS2.4 GB 5.7 GB
Fits Get file →
IQ2_S2.5 GB 5.8 GB
Fits Get file →
IQ2_M2.7 GB 6.0 GB
Fits Get file →
Q2_K_S2.7 GB 6.0 GB
Fits Get file →
Q2_K2.9 GB 6.2 GB
Fits Get file →
IQ3_XXS3.0 GB 6.4 GB
Fits Get file →
IQ3_XS3.3 GB 6.6 GB
Fits Get file →
IQ3_S3.4 GB 6.7 GB
Fits Get file →
Q3_K_S3.4 GB 6.7 GB
Fits Get file →
IQ3_M3.5 GB 6.8 GB
Fits Get file →
Q3_K3.8 GB 7.1 GB
Fits Get file →
Q3_K_L4.1 GB 7.4 GB
Tight Get file →
IQ4_XS4.2 GB 7.5 GB
Tight Get file →
IQ4_NL4.4 GB 7.8 GB
Tight Get file →
Q4_K_S4.5 GB 7.8 GB
Tight Get file →
Q4_K4.7 GB 8.1 GB
Too big Get file →
Q5_K_S5.4 GB 8.7 GB
Too big Get file →
Q5_K5.5 GB 8.9 GB
Too big Get file →
Q6_K6.4 GB 9.7 GB
Too big Get file →
Q8_08.3 GB 11.6 GB
Too big Get file →
BF1615.6 GB 18.9 GB
Too big Get file →
—15.6 GB 18.9 GB
Too big Get file →

For 8 GB VRAM, the IQ1_S or IQ1_M quantizations are recommended, each using about 5 GB of VRAM at 8 k context. If more VRAM is available, IQ2_S or Q2_K_S provide a balance between size and quality. For the highest quality within 12 GB, Q4_K or Q5_K_S are suitable.

What GPU do you need for neo_7b_instruct_v0.1?

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 Q2_K_S (2.7 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_S (4.5 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 11.6 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (15.6 GB file, about 18.9 GB in use).

Which neo_7b_instruct_v0.1 quant should you choose?

IQ3_M (3.5 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 1.7 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
Parameters7.79B
Layers28
Trained context8,192 tokens
KV cache (fp16)336 KB per token

Source

Quantized bylegraphista
FamilyNeo
Licenseapache-2.0
Downloads (HF)2,682
Last updated2024-05-31

Frequently asked questions about neo_7b_instruct_v0.1

How much VRAM does neo_7b_instruct_v0.1 need?

About 6.8 GB at IQ3_M with an 8K context window. That is the 3.5 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 neo_7b_instruct_v0.1 on an 8 GB GPU?

Yes, with Q4_K_S: the 4.5 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of neo_7b_instruct_v0.1 GGUF?

It depends on the quant: IQ1_S is 1.7 GB, IQ1_M is 1.9 GB, IQ2_XXS is 2.1 GB, IQ2_XS is 2.4 GB, IQ2_S is 2.5 GB, IQ2_M is 2.7 GB and 19 more.

What context length does neo_7b_instruct_v0.1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.8 GB at 8K and 2.8 GB at 8K.

Where can I download neo_7b_instruct_v0.1 GGUF?

The files are on Hugging Face in the legraphista/neo_7b_instruct_v0.1-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 neo_7b_instruct_v0.1 use?

Hugging Face lists the license as apache-2.0. 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 Neo 7B Instruct v0.1 on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantizations, which use about 5 GB of VRAM at 8 k context.

Does this model support vision tasks?

No, Neo 7B Instruct v0.1 does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of neo_7b_instruct_v0.1

Similar models

Browse all →

More from legraphista

All by legraphista →

More Neo models

All Neo →

Other small models

All small models →