DI

dictalm2.0 instruct

DictalmGGUF by dicta-ilUpdated 2024-07-10
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

dictalm2.0 instruct needs about 5.9 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 2 quants, from 4.4 GB (Q4_K_M) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

DictaLM‑2.0 Instruct – 7.25B Hebrew‑focused instruction model

DictaLM‑2.0 Instruct is a 7.25 billion‑parameter LLM fine‑tuned for instruction following. It builds on the DictaLM‑2.0 base, adding conversational datasets. The model supports a 32 768‑token context window.

Good at

  • Hebrew text generation
  • Instruction following
  • Chat‑style interactions

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • Apache‑2.0 license

Best for

  • Hebrew language chatbots
  • Instruction‑driven Q&A
  • Text completion in Hebrew

Who it’s for. Developers building Hebrew‑centric chat applications or research projects needing instruction‑tuned language models. The model is suitable for users who can run GGUF files with llama.cpp or LM Studio.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
F1614.5 GB 16.1 GB
Too big Get file →

For 8 GB VRAM, use the Q4_K_M quantized file (4.37 GB, ~5.9 GB memory at 8 k context). For higher precision, the F16 file (14.5 GB, ~16.1 GB memory) requires more GPU memory but offers full‑precision performance.

What GPU do you need for dictalm2.0 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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).

Which dictalm2.0 instruct quant should you choose?

Q4_K_M is the usual starting point for dictalm2.0 instruct: it balances file size and quality well. Here it is a 4.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.25B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bydicta-il
FamilyDictalm
Licenseapache-2.0
Downloads (HF)661
Last updated2024-07-10

Frequently asked questions about dictalm2.0 instruct

How much VRAM does dictalm2.0 instruct need?

About 5.9 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 dictalm2.0 instruct on an 8 GB GPU?

Yes, with Q4_K_M: the 4.4 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of dictalm2.0 instruct GGUF?

It depends on the quant: Q4_K_M is 4.4 GB, F16 is 14.5 GB.

What context length does dictalm2.0 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 dictalm2.0 instruct GGUF?

The files are on Hugging Face in the dicta-il/dictalm2.0-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 dictalm2.0 instruct 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 DictaLM‑2.0 Instruct on 8 GB VRAM?

Yes, the Q4_K_M quantized model (4.37 GB) uses about 5.9 GB of VRAM at 8 k context, fitting within an 8 GB GPU.

Does the model support vision tasks?

No, the model is purely text‑based and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of dictalm2.0

Similar models

Browse all →

More from dicta-il

All by dicta-il →

More Dictalm models

All Dictalm →

Other small models

All small models →