SO

SOLAR-10.7B-Instruct-v1.0

SolarGGUF by duyntnetUpdated 2024-05-04
Download on Hugging Face
Parameters10.7B
Context4K
Layers48
Architecturellama
Smallest quant2.4 GB
Quick answer

SOLAR-10.7B-Instruct-v1.0 needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 27 quants, from 2.4 GB (IQ1_S) to 11.4 GB (Q8_0).

SOLAR-10.7B-Instruct: 10.7B llama model for single-turn instruction

SOLAR-10.7B-Instruct is a 10.7B parameter llama model fine‑tuned for single‑turn instruction following. It supports a 4096 token context window and is available in multiple GGUF quantizations.

Good at

  • Single‑turn instruction following
  • Llama architecture compatibility
  • 4096 token context

Limits

  • Not suited for multi‑turn chat
  • Requires at least 8.2 GB VRAM for Q4_0 quant
  • License is other

Best for

  • Quick instruction‑based queries
  • Prototype single‑turn bots
  • Testing instruction fine‑tuning

Who it’s for. Developers building lightweight instruction models and researchers needing a 10.7B llama base for single‑turn tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 3.7 GB
Fits Get file →
IQ1_M2.6 GB 3.9 GB
Fits Get file →
IQ2_XXS2.9 GB 4.2 GB
Fits Get file →
IQ2_XS3.2 GB 4.5 GB
Fits Get file →
IQ2_S3.4 GB 4.7 GB
Fits Get file →
IQ2_M3.7 GB 5.0 GB
Fits Get file →
Q2_K_S3.7 GB 5.0 GB
Fits Get file →
Q2_K4.0 GB 5.3 GB
Fits Get file →
IQ3_XXS4.2 GB 5.5 GB
Fits Get file →
IQ3_XS4.4 GB 5.8 GB
Fits Get file →
Q3_K_S4.7 GB 6.0 GB
Fits Get file →
IQ3_S4.7 GB 6.0 GB
Fits Get file →
IQ3_M4.8 GB 6.2 GB
Fits Get file →
Q3_K_M5.2 GB 6.5 GB
Fits Get file →
Q3_K_L5.7 GB 7.0 GB
Fits Get file →
IQ4_XS5.8 GB 7.1 GB
Fits Get file →
Q4_06.1 GB 7.4 GB
Tight Get file →
IQ4_NL6.1 GB 7.4 GB
Tight Get file →
Q4_K_S6.1 GB 7.4 GB
Tight Get file →
Q4_K_M6.5 GB 7.8 GB
Tight Get file →
Q4_16.7 GB 8.0 GB
Too big Get file →
Q5_K_S7.4 GB 8.7 GB
Too big Get file →
Q5_07.4 GB 8.7 GB
Too big Get file →
Q5_K_M7.6 GB 8.9 GB
Too big Get file →
Q5_18.1 GB 9.4 GB
Too big Get file →
Q6_K8.8 GB 10.1 GB
Too big Get file →
Q8_011.4 GB 12.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 6.09 GB, estimated 8.2 GB memory). For 10 GB VRAM, use Q5_0 (file size 7.42 GB, estimated 9.5 GB memory). For 12 GB VRAM, use Q6_K (file size 8.81 GB, estimated 10.9 GB memory).

What GPU do you need for SOLAR-10.7B-Instruct-v1.0?

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 (3.7 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ4_XS (5.8 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.5 GB in use).

Which SOLAR-10.7B-Instruct-v1.0 quant should you choose?

Q4_K_M is the usual starting point for SOLAR-10.7B-Instruct-v1.0: it balances file size and quality well. Here it is a 6.5 GB file.

The Q8_0 file is 11.4 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 2.4 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
Parameters10.7B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized byduyntnet
FamilySolar
Licenseother
Downloads (HF)1,167
Last updated2024-05-04

Frequently asked questions about SOLAR-10.7B-Instruct-v1.0

How much VRAM does SOLAR-10.7B-Instruct-v1.0 need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 SOLAR-10.7B-Instruct-v1.0 on an 8 GB GPU?

Yes, with IQ4_XS: the 5.8 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 SOLAR-10.7B-Instruct-v1.0 GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ1_M is 2.6 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.2 GB, IQ2_S is 3.4 GB, IQ2_M is 3.7 GB and 21 more.

What context length does SOLAR-10.7B-Instruct-v1.0 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download SOLAR-10.7B-Instruct-v1.0 GGUF?

The files are on Hugging Face in the duyntnet/SOLAR-10.7B-Instruct-v1.0-imatrix-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 SOLAR-10.7B-Instruct-v1.0 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 SOLAR-10.7B-Instruct on 8 GB VRAM?

Yes, with Q4_0 quant it needs about 8.2 GB memory, so 8 GB VRAM is borderline.

Is it suitable for multi‑turn chat?

No, it is fine‑tuned for single‑turn conversation.

What license does it use?

The license is listed as "other", check the repo for details.

Similar models

Browse all →

More from duyntnet

All by duyntnet →

More Solar models

All Solar →

Other medium models

All medium models →