What are the hardware requirements for Dictalm2.0 Instruct AWQ?

Dictalm2.0 Instruct AWQ requires approximately 4.2 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Dictalm2.0 Instruct AWQ and how large is it?

Dictalm2.0 Instruct AWQ is developed by dicta-il, a model with 7.3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Dictalm2.0 Instruct AWQ?

Dictalm2.0 Instruct AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Dictalm2.0 Instruct AWQ by dicta-il — VRAM 4.2GB, 32K context

Name: Dictalm2.0 Instruct AWQ
Author: dicta-il

Dictalm2.0 Instruct AWQ is an open-source language model by dicta-il. Features: 7.3b LLM, VRAM: 4.2GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

Arxiv:2407.07080 4-bit Awq Base model:dicta-il/dictalm2.0 Base model:quantized:dicta-il/... Conversational En He Instruct Instruction-tuned Mistral Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/dicta-il/dictalm2.0-instruct-AWQ

Dictalm2.0 Instruct AWQ Parameters and Internals

Model Type

instruct-tuned, text generation

Use Cases

Limitations:

No moderation mechanisms in place.

Additional Notes

Available as a chat template via the apply_chat_template method.

Supported Languages

en (English), he (Hebrew)

Training Details

Methodology:

Instruct fine-tuning using a variety of conversation datasets.

Model Architecture:

Zephyr-7B-beta

Input Output

Input Format:

Expect instruction prompts to be surrounded by `[INST]` and `[/INST]` tokens.

Accepted Modalities:

text

LLM Name	Dictalm2.0 Instruct AWQ
Repository 🤗	https://huggingface.co/dicta-il/dictalm2.0-instruct-AWQ
Base Model(s)	dicta-il/dictalm2.0 dicta-il/dictalm2.0
Model Size	7.3b
Required VRAM	4.2 GB
Updated	2026-08-07
Maintainer	dicta-il
Model Type	mistral
Instruction-Based	Yes
Model Files	4.2 GB
Supported Languages	en he
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	33152
Torch Data Type	float16

Rank the Dictalm2.0 Instruct AWQ capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Dictalm2.0 Instruct AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Dictalm2.0 Instruct	32K / 14.5 GB	2791	25
Dictalm2 It Qa Fine Tune	32K / 14.5 GB	26	7
... Fine Tuned Alpaca Gpt4 Hebrew	32K / 14.5 GB	201	0
Dictalm2.0 Instruct Fine Tuned	32K / 14.5 GB	21	0
Dictalm2.0 Instruct GPTQ	32K / 4.2 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than dicta-il/dictalm2.0-instruct-AWQ.