LLM EXPLORER 60,062 MODELS INDEXED

Falcon H1 34B Instruct GPTQ Int8 by tiiuae

By tiiuae · 65 downloads
HF Repo ↗ Copy URL

Falcon H1 34B Instruct GPTQ Int8 is an open-source language model by tiiuae. Features: 34b LLM, VRAM: 44.3GB, Context: 8K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.18.

  8-bit Base model:quantized:tiiuae/fa... Base model:tiiuae/falcon-h1-34...   Conversational   Endpoints compatible   Falcon-h1   Falcon h1   Gptq   Instruct   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/tiiuae/Falcon-H1-34B-Instruct-GPTQ-Int8 

Falcon H1 34B Instruct GPTQ Int8 Parameters and Internals

LLM NameFalcon H1 34B Instruct GPTQ Int8
Repository 🤗https://huggingface.co/tiiuae/Falcon-H1-34B-Instruct-GPTQ-Int8 
Base Model(s)  Falcon H1 34B Instruct   tiiuae/Falcon-H1-34B-Instruct
Model Size34b
Required VRAM44.3 GB
Updated2026-08-04
Maintainertiiuae
Model Typefalcon_h1
Instruction-BasedYes
Model Files  4.0 GB: 1-of-12   4.0 GB: 2-of-12   4.0 GB: 3-of-12   4.0 GB: 4-of-12   4.0 GB: 5-of-12   4.0 GB: 6-of-12   4.0 GB: 7-of-12   4.0 GB: 8-of-12   4.0 GB: 9-of-12   4.0 GB: 10-of-12   1.6 GB: 11-of-12   2.7 GB: 12-of-12
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureFalconH1ForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.52.0.dev0
Tokenizer ClassPreTrainedTokenizer
Padding Token<|pad|>
Vocabulary Size261120
Torch Data Typebfloat16

Best Alternatives to Falcon H1 34B Instruct GPTQ Int8

Best Alternatives
Context / RAM
Downloads
Likes
...lcon H1 34B Instruct GPTQ Int48K / 32.2 GB1122
Falcon H1 34B Instruct256K / 67 GB172652
Note: green Score (e.g. "73.2") means that the model is better than tiiuae/Falcon-H1-34B-Instruct-GPTQ-Int8.