LLM EXPLORER 59,358 MODELS INDEXED

CodeLlama 70B Instruct Hf GGUF by second-state

By second-state · 487 downloads
HF Repo ↗ Copy URL

CodeLlama 70B Instruct Hf GGUF is an open-source language model by second-state. Features: 70b LLM, VRAM: 25.5GB, Context: 4K, License: llama2, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.11.

Base model:codellama/codellama... Base model:quantized:codellama...   Code   Codegen   Conversational   Endpoints compatible   Gguf   Instruct   Llama   Llama2   Q2   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/second-state/CodeLlama-70b-Instruct-hf-GGUF 

CodeLlama 70B Instruct Hf GGUF Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model quantized by Second State Inc. for text generation. Quantized Models Summary: Q2_K (2 Bits, 25.5 GB): Smallest, significant quality loss. Q3_K_L (3 Bits, 36.1 GB): Small, substantial quality loss. Q3_K_M (3 Bits, 33.3 GB): Very small, high quality loss. Q3_K_S (3 Bits, 29.9 GB): Very small, high quality loss. Q4_0 (4 Bits, 38.9 GB): Legacy; high quality loss, prefer Q3_K_M. Q4_K_M (4 Bits, 41.4 GB): Medium, balanced quality - recommended. Q4_K_S (4 Bits, 39.2 GB): Small, greater quality loss. Q5_0 (5 Bits, 47.5 GB): Legacy; medium, balanced quality, prefer Q4_K_M. Q5_K_M (5 Bits, 48.8 GB): Large, very low quality loss - recommended. Q5_K_S (5 Bits, 47.5 GB): Large, low quality loss - recommended.
Supported Languages 
code (high)
Input Output 
Accepted Modalities:
text
LLM NameCodeLlama 70B Instruct Hf GGUF
Repository 🤗https://huggingface.co/second-state/CodeLlama-70b-Instruct-hf-GGUF 
Model NameCodeLlama 70B Instruct
Model Creatorcodellama
Base Model(s)  CodeLlama 70B Instruct Hf   codellama/CodeLlama-70b-Instruct-hf
Model Size70b
Required VRAM25.5 GB
Updated2026-07-28
Maintainersecond-state
Model Typellama
Instruction-BasedYes
Model Files  25.5 GB   36.1 GB   33.3 GB   29.9 GB   38.9 GB   41.4 GB   39.2 GB   47.5 GB   48.8 GB   47.5 GB
Supported Languagescode
GGUF QuantizationYes
Quantization Typegguf|q2|q4_k|q5_k
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.1
Vocabulary Size32016
Torch Data Typebfloat16

Best Alternatives to CodeLlama 70B Instruct Hf GGUF

Best Alternatives
Context / RAM
Downloads
Likes
...Llama 70B Instruct Hf 4bit MLX4K / 39.1 GB41725
...70B Instruct Nf4 Fp16 Upscaled4K / 138.7 GB101
...70B Instruct Hf 5.0bpw H6 EXL22K / 43.6 GB56
...70B Instruct Hf 2.4bpw H6 EXL22K / 21.3 GB61
...0B Instruct Hf 2.65bpw H6 EXL22K / 23.4 GB53
...70B Instruct Hf 4.0bpw H6 EXL22K / 35.1 GB61
CodeLlama 70B Instruct Hf4K / 72.3 GB72924
Code Llama 70B Python Instruct4K / 138.1 GB51
CodeLlama 70B Instruct Hf4K / 72.3 GB463210
CodeLlama 70B Instruct AWQ4K / 36.6 GB29713
Note: green Score (e.g. "73.2") means that the model is better than second-state/CodeLlama-70b-Instruct-hf-GGUF.