EX

EXAONE 3.5 7.8B Instruct

ExaoneGGUF by mradermacherUpdated 2024-12-09
Download on Hugging Face
Parameters7.82B
Context32K
Layers32
Architectureexaone
Smallest quant1.9 GB
Quick answer

EXAONE 3.5 7.8B Instruct needs about 6.3 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 1.9 GB (IQ1_S) to 6.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

EXAONE 3.5 7.8B Instruct – instruction‑tuned bilingual model

EXAONE 3.5 7.8B Instruct is a 7.82B‑parameter instruction‑tuned model supporting up to 32,768 context tokens. It is optimized for conversational and long‑context tasks. The model is available in multiple GGUF quantizations for efficient deployment.

Good at

  • Long‑context instruction following
  • Bilingual English‑Korean dialogue
  • Efficient inference with GGUF

Limits

  • No vision support
  • Requires 32K context for full capability
  • License is other, not open source

Best for

  • Chatbots needing long context
  • Translation assistance
  • Content generation with extended prompts

Who it’s for. Developers and researchers who need a bilingual instruction model with large context handling. Suitable for edge deployment when paired with a compatible quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.9 GB 3.5 GB
Fits Get file →
IQ1_M2.1 GB 3.6 GB
Fits Get file →
IQ2_XXS2.3 GB 3.9 GB
Fits Get file →
IQ2_XS2.5 GB 4.1 GB
Fits Get file →
IQ2_S2.6 GB 4.2 GB
Fits Get file →
IQ2_M2.8 GB 4.4 GB
Fits Get file →
Q2_K_S2.9 GB 4.4 GB
Fits Get file →
Q2_K3.1 GB 4.6 GB
Fits Get file →
IQ3_XXS3.2 GB 4.7 GB
Fits Get file →
IQ3_XS3.4 GB 5.0 GB
Fits Get file →
Q3_K_S3.5 GB 5.1 GB
Fits Get file →
IQ3_S3.5 GB 5.1 GB
Fits Get file →
IQ3_M3.6 GB 5.2 GB
Fits Get file →
Q3_K_M3.9 GB 5.5 GB
Fits Get file →
Q3_K_L4.2 GB 5.8 GB
Fits Get file →
IQ4_XS4.3 GB 5.9 GB
Fits Get file →
Q4_04.5 GB 6.1 GB
Fits Get file →
Q4_04.5 GB 6.1 GB
Fits Get file →
Q4_04.5 GB 6.1 GB
Fits Get file →
Q4_04.5 GB 6.1 GB
Fits Get file →
Q4_K_S4.5 GB 6.1 GB
Fits Get file →
Q4_K_M4.8 GB 6.3 GB
Fits Get file →
Q5_K_S5.4 GB 7.0 GB
Fits Get file →
Q5_K_M5.6 GB 7.1 GB
Fits Get file →
Q6_K6.4 GB 8.0 GB
Tight Get file →

For 8 GB VRAM, use Q4_0 (4.51 GB) or Q4_K_S (4.54 GB). For 12 GB VRAM, Q5_K_S (5.44 GB) or Q5_K_M (5.57 GB) provide a balance of quality and memory. For 16 GB VRAM, Q6_K (6.42 GB) offers the highest precision within budget. Memory estimates are approximate.

What GPU do you need for EXAONE 3.5 7.8B 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: the best quant that fits is IQ2_XXS (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.4 GB file, about 8.0 GB in use).

Which EXAONE 3.5 7.8B Instruct quant should you choose?

Q4_K_M is the usual starting point for EXAONE 3.5 7.8B Instruct: it balances file size and quality well. Here it is a 4.8 GB file.

If memory is tight, the smallest file is IQ1_S at 1.9 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

Architectureexaone
Parameters7.82B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyExaone
Licenseother
Downloads (HF)867
Last updated2024-12-09

Frequently asked questions about EXAONE 3.5 7.8B Instruct

How much VRAM does EXAONE 3.5 7.8B Instruct need?

About 6.3 GB at Q4_K_M with an 8K context window. That is the 4.8 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 EXAONE 3.5 7.8B Instruct on an 8 GB GPU?

Yes, with Q6_K: the 6.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of EXAONE 3.5 7.8B Instruct GGUF?

It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.1 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 19 more.

What context length does EXAONE 3.5 7.8B Instruct 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 EXAONE 3.5 7.8B Instruct GGUF?

The files are on Hugging Face in the mradermacher/EXAONE-3.5-7.8B-Instruct-i1-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 EXAONE 3.5 7.8B Instruct 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 EXAONE 3.5 7.8B Instruct on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantizations, which are 4.51 GB and 4.54 GB respectively, will fit within 8 GB VRAM with some overhead.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What is the maximum context length I can use?

The model supports up to 32,768 tokens of context.

Other GGUFs of EXAONE-3.5-7.8B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Exaone models

All Exaone →

Other small models

All small models →