TH

ThaiLLM 8B SFT IQ

ThaillmGGUF by mradermacherUpdated 2026-01-17
Download on Hugging Face
Parameters8.19B
Context32K
Layers36
Architectureqwen3
Smallest quant0.0 GB
Quick answer

ThaiLLM 8B SFT IQ needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 6.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

ThaiLLM 8B SFT IQ – Thai medical QA model

ThaiLLM 8B SFT IQ is a decoder‑only causal language model fine‑tuned for Thai medical information query and citation‑grounded question answering. It is designed for retrieval‑augmented generation workflows and outputs strict JSON answers.

Good at

  • Medical RAG in Thai
  • Citation‑grounded QA
  • Strict JSON output

Limits

  • Context length 4096 tokens
  • No vision support
  • Not for medical diagnosis

Best for

  • Medical document QA
  • Medical education tools
  • RAG pipelines

Who it’s for. Developers building Thai medical question‑answering systems that require citation‑grounded responses. The model is not intended for clinical decision support or patient‑facing advice.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ1_S2.1 GB 3.8 GB
Fits Get file →
IQ1_M2.3 GB 4.0 GB
Fits Get file →
IQ2_XXS2.5 GB 4.2 GB
Fits Get file →
IQ2_XS2.7 GB 4.4 GB
Fits Get file →
IQ2_S2.9 GB 4.6 GB
Fits Get file →
IQ2_M3.1 GB 4.8 GB
Fits Get file →
Q2_K_S3.1 GB 4.8 GB
Fits Get file →
Q2_K3.3 GB 5.0 GB
Fits Get file →
IQ3_XXS3.4 GB 5.1 GB
Fits Get file →
IQ3_XS3.6 GB 5.3 GB
Fits Get file →
Q3_K_S3.8 GB 5.5 GB
Fits Get file →
IQ3_S3.8 GB 5.5 GB
Fits Get file →
IQ3_M3.9 GB 5.6 GB
Fits Get file →
Q3_K_M4.1 GB 5.8 GB
Fits Get file →
Q3_K_L4.4 GB 6.1 GB
Fits Get file →
IQ4_XS4.6 GB 6.3 GB
Fits Get file →
Q4_04.8 GB 6.5 GB
Fits Get file →
IQ4_NL4.8 GB 6.5 GB
Fits Get file →
Q4_K_S4.8 GB 6.5 GB
Fits Get file →
Q4_K_M5.0 GB 6.7 GB
Fits Get file →
Q4_15.2 GB 7.0 GB
Fits Get file →
Q5_K_S5.7 GB 7.4 GB
Tight Get file →
Q5_K_M5.9 GB 7.6 GB
Tight Get file →
Q6_K6.7 GB 8.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.12 GB, memory 3.8 GB) or IQ1_M (2.26 GB, 4 GB). For 12 GB VRAM, IQ2_XS (2.7 GB, 4.4 GB) or IQ2_S (2.86 GB, 4.6 GB) are suitable. Larger VRAM allows higher‑quality quants such as Q4_K_M (5.03 GB, 6.7 GB).

What GPU do you need for ThaiLLM 8B SFT IQ?

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: the best quant that fits is IQ1_M (2.3 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.1 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.4 GB in use).

Which ThaiLLM 8B SFT IQ quant should you choose?

Q4_K_M is the usual starting point for ThaiLLM 8B SFT IQ: it balances file size and quality well. Here it is a 5.0 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters8.19B
Layers36
Trained context32,768 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
FamilyThaillm
Downloads (HF)748
Last updated2026-01-17

Frequently asked questions about ThaiLLM 8B SFT IQ

How much VRAM does ThaiLLM 8B SFT IQ need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 ThaiLLM 8B SFT IQ on an 8 GB GPU?

Yes, with Q5_K_M: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ThaiLLM 8B SFT IQ GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.1 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB and 19 more.

What context length does ThaiLLM 8B SFT IQ support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download ThaiLLM 8B SFT IQ GGUF?

The files are on Hugging Face in the mradermacher/ThaiLLM-8B-SFT-IQ-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run ThaiLLM 8B SFT IQ on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quants will fit within 8 GB VRAM, as they require approximately 3.8–4 GB of memory at 8 k context.

Does the model support vision tasks?

No, the model does not include vision capabilities.

Is the model suitable for medical diagnosis?

No, the model is not intended for medical diagnosis or treatment decisions.

Other GGUFs of ThaiLLM-8B-SFT-IQ

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Thaillm models

All Thaillm →

Other small models

All small models →