scb10x llama 3 typhoon v1.5x 70b instruct needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 22 quants, from 11.4 GB (Q8_0) to 57.9 GB (Q6_K).
70B Llama‑3 instruct model optimized for Thai and English
scb10x llama 3 typhoon v1.5x 70b instruct is a 70.6B parameter decoder‑only model based on Llama architecture. It supports Thai and English instruction following and is licensed under llama3. The model was quantized by RichardErkhov and is available in multiple GGUF formats.
Good at
- Instruction following
- Thai language understanding
- Reasoning tasks
Limits
- No vision support
- Requires 8k context for full performance
- Large VRAM needed for higher quants
Best for
- Chatbots in Thai and English
- Retrieval‑augmented generation
- Complex reasoning queries
Who it’s for. Developers building multilingual LLM applications that require Thai language support. Researchers needing a large instruct model for cross‑lingual tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 11.4 GB | 14.6 GB | Too big | Get file → | |
| Q5_K | 26.0 GB | 29.2 GB | Too big | Get file → | |
| Q2_K | 26.4 GB | 29.6 GB | Too big | Get file → | |
| IQ3_XS | 29.3 GB | 32.5 GB | Too big | Get file → | |
| IQ3_S | 30.9 GB | 34.1 GB | Too big | Get file → | |
| Q3_K_S | 30.9 GB | 34.1 GB | Too big | Get file → | |
| IQ3_M | 31.9 GB | 35.1 GB | Too big | Get file → | |
| Q3_K | 34.3 GB | 37.5 GB | Too big | Get file → | |
| Q3_K_M | 34.3 GB | 37.5 GB | Too big | Get file → | |
| Q4_1 | 37.0 GB | 40.2 GB | Too big | Get file → | |
| Q3_K_L | 37.1 GB | 40.3 GB | Too big | Get file → | |
| IQ4_XS | 38.3 GB | 41.5 GB | Too big | Get file → | |
| Q4_0 | 40.0 GB | 43.2 GB | Too big | Get file → | |
| Q5_K_M | 40.2 GB (2 parts) | 43.4 GB | Too big | Get file → | |
| IQ4_NL | 40.3 GB (2 parts) | 43.5 GB | Too big | Get file → | |
| Q4_K_S | 40.3 GB (2 parts) | 43.5 GB | Too big | Get file → | |
| Q4_K | 42.5 GB (2 parts) | 45.7 GB | Too big | Get file → | |
| Q4_K_M | 42.5 GB (2 parts) | 45.7 GB | Too big | Get file → | |
| Q5_0 | 45.7 GB (2 parts) | 48.8 GB | Too big | Get file → | |
| Q5_K_S | 48.7 GB (2 parts) | 51.8 GB | Too big | Get file → | |
| Q5_1 | 53.0 GB (2 parts) | 56.2 GB | Too big | Get file → | |
| Q6_K | 57.9 GB (2 parts) | 61.1 GB | Too big | Get file → |
For 8‑12 GB VRAM, use Q8_0 (11.44 GB file, 14.6 GB memory). For 16‑20 GB VRAM, Q5_K (25.98 GB file, 29.2 GB memory) or Q5_K_M (40.17 GB file, 43.4 GB memory). For 24‑30 GB VRAM, Q4_K (42.52 GB file, 45.7 GB memory).
What GPU do you need for scb10x llama 3 typhoon v1.5x 70b instruct?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 14.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K (42.5 GB file, about 45.7 GB in use).
Which scb10x llama 3 typhoon v1.5x 70b instruct quant should you choose?
Q4_K_M is the usual starting point for scb10x llama 3 typhoon v1.5x 70b instruct: it balances file size and quality well. Here it is a 42.5 GB file.
The Q8_0 file is 11.4 GB, about 0.3 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 Q8_0 at 11.4 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about scb10x llama 3 typhoon v1.5x 70b instruct
How much VRAM does scb10x llama 3 typhoon v1.5x 70b instruct need?
About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 scb10x llama 3 typhoon v1.5x 70b instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of scb10x llama 3 typhoon v1.5x 70b instruct GGUF?
It depends on the quant: Q8_0 is 11.4 GB, Q5_K is 26.0 GB, Q2_K is 26.4 GB, IQ3_XS is 29.3 GB, IQ3_S is 30.9 GB, Q3_K_S is 30.9 GB and 16 more.
What context length does scb10x llama 3 typhoon v1.5x 70b instruct support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.
Where can I download scb10x llama 3 typhoon v1.5x 70b instruct GGUF?
The files are on Hugging Face in the RichardErkhov/scb10x_-_llama-3-typhoon-v1.5x-70b-instruct-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 scb10x llama 3 typhoon v1.5x 70b instruct use?
Hugging Face lists the license as llama3. 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?
Use the Q8_0 quant; it requires 14.6 GB memory at 8k context, so 8 GB VRAM is insufficient.
Does the model support vision inputs?
No, the model is a text‑only decoder‑only model.
What license applies to this model?
The model is licensed under the llama3 community license.