DI

dictalm2.0

DictalmGGUF by mradermacherUpdated 2024-07-11
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

dictalm2.0 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 15 quants, from 2.7 GB (Q2_K) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

DictaLM 2.0 – 7.25B‑parameter Hebrew‑focused LLM

DictaLM 2.0 is a 7.25B‑parameter model based on Mistral‑7B‑v0.1, trained on 190B tokens of Hebrew and English. It uses an extended tokenizer with 1,000 Hebrew tokens, improving compression from 5.78 to 2.76 tokens per word. The model is released under Apache‑2.0.

Good at

  • Hebrew text generation
  • Instruction following in Hebrew
  • Large context handling (32,768 tokens)

Limits

  • No vision support
  • No moderation mechanisms
  • Requires 8,000‑token context for estimates

Best for

  • Hebrew language chatbots
  • Content creation in Hebrew
  • Academic research on Hebrew NLP

Who it’s for. Researchers and developers needing a Hebrew‑specialized LLM. The model is open‑source and can be run locally with llama.cpp or similar frameworks.

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 4.7 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_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_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →
F1614.5 GB 16.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (5.7 GB memory) or Q4_K_M (5.9 GB). For 12 GB VRAM, Q5_K_S (6.6 GB) or Q5_K_M (6.7 GB) are suitable. For 16 GB VRAM, Q6_K (7.5 GB) or Q8_0 (9.3 GB) provide higher precision.

What GPU do you need for dictalm2.0?

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 Q6_K (5.9 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).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 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 quant should you choose?

Q4_K_M is the usual starting point for dictalm2.0: 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
Parameters7.25B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyDictalm
Licenseapache-2.0
Downloads (HF)973
Last updated2024-07-11

Frequently asked questions about dictalm2.0

How much VRAM does dictalm2.0 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 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 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 dictalm2.0 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_M is 3.5 GB and 9 more.

What context length does dictalm2.0 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 GGUF?

The files are on Hugging Face in the mradermacher/dictalm2.0-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 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 on 8 GB VRAM?

Yes, use Q4_K_S or Q4_K_M quantizations, which require about 5.7–5.9 GB of VRAM at 8,000‑token context.

Does the model support vision inputs?

No, DictaLM 2.0 is a text‑only model and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Other GGUFs of dictalm2.0

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Dictalm models

All Dictalm →

Other small models

All small models →