TY

Typhoon 7b Instruct 02 19 2024

TyphoonGGUF by RichardErkhovUpdated 2024-09-08
Download on Hugging Face
Parameters7.27B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

Typhoon 7b Instruct 02 19 2024 needs about 6.0 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 2.7 GB (Q2_K) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Typhoon 7b Instruct 02 19 2024 – a 7.27B Thai‑English instruction model

Typhoon 7b Instruct 02 19 2024 is a 7.27B parameter decoder‑only model based on the Typhoon family. It supports Thai and English instruction following and is released under the Apache‑2.0 license. The model is trained on a diverse instruction tuning dataset with over 1 million rows.

Good at

  • Instruction following in Thai and English
  • ChatML chat template support
  • Large context of 32 768 tokens

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • Still under development with guardrails

Best for

  • Local Thai language chatbots
  • Instruction‑based text generation
  • Fine‑tuning for Thai‑English tasks

Who it’s for. Developers building Thai‑English instruction models or chat applications. The model is suitable for users who need a local LLM with a moderate parameter count and a permissive license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.8 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_K3.5 GB 5.1 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_XS4.0 GB 5.5 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.2 GB 5.7 GB
Fits Get file →
IQ4_NL4.2 GB 5.7 GB
Fits Get file →
Q4_K4.4 GB 6.0 GB
Fits Get file →
Q4_K_M4.4 GB 6.0 GB
Fits Get file →
Q4_14.6 GB 6.1 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K5.2 GB 6.7 GB
Fits Get file →
Q5_K_M5.2 GB 6.7 GB
Fits Get file →
Q5_15.5 GB 7.0 GB
Fits Get file →
Q6_K6.0 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (4.13 GB file, 5.7 GB memory) or Q4_K_S (4.16 GB file, 5.7 GB memory). For 12 GB VRAM, Q5_0 (5.02 GB file, 6.6 GB memory) or Q5_K (5.15 GB file, 6.7 GB memory) provide a balance of quality and memory. Larger VRAM allows Q6_K (5.96 GB file, 7.5 GB memory) or Q8_0 (7.72 GB file, 9.3 GB memory).

What GPU do you need for Typhoon 7b Instruct 02 19 2024?

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 Q4_K (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.0 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).

Which Typhoon 7b Instruct 02 19 2024 quant should you choose?

Q4_K_M is the usual starting point for Typhoon 7b Instruct 02 19 2024: 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 Q2_K at 2.7 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
Parameters7.27B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyTyphoon
Licenseapache-2.0
Downloads (HF)953
Last updated2024-09-08

Frequently asked questions about Typhoon 7b Instruct 02 19 2024

How much VRAM does Typhoon 7b Instruct 02 19 2024 need?

About 6.0 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 Typhoon 7b Instruct 02 19 2024 on an 8 GB GPU?

Yes, with Q6_K: the 6.0 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 Typhoon 7b Instruct 02 19 2024 GGUF?

It depends on the quant: Q2_K is 2.7 GB, IQ3_XS is 3.0 GB, Q3_K_S is 3.2 GB, IQ3_S is 3.2 GB, IQ3_M is 3.3 GB, Q3_K is 3.5 GB and 16 more.

What context length does Typhoon 7b Instruct 02 19 2024 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 Typhoon 7b Instruct 02 19 2024 GGUF?

The files are on Hugging Face in the RichardErkhov/scb10x_-_typhoon-7b-instruct-02-19-2024-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 Typhoon 7b Instruct 02 19 2024 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 this model on 8 GB VRAM?

Yes, use Q4_0 or Q4_K_S quantizations, which require about 5.7 GB memory at 8 k context.

Does this model support vision tasks?

No, it is a text‑only decoder‑only model.

What license does it use?

Apache‑2.0, which allows commercial use and modification.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Typhoon models

All Typhoon →

Other small models

All small models →