LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Koishi 8x7b Qlora Gguf by ewof

 »  All LLMs  »  ewof  »  Koishi 8x7b Qlora Gguf   URL Share it on

  46   

Koishi 8x7b Qlora Gguf is an open-source language model by ewof. Features: LLM, VRAM: 15.6GB, MoE, Quantized, Instruction-Based, LLM Explorer Score: 0.11.

Dataset:ewof/koishi-instruct-m...   Endpoints compatible   Ggml   Gguf   Instruct   Mixtral   Moe   Q2   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/ewof/koishi-8x7b-qlora-gguf 

Koishi 8x7b Qlora Gguf Benchmarks

LLME Score: 0.10646
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Koishi 8x7b Qlora Gguf (ewof/koishi-8x7b-qlora-gguf)
🌟 Advertise your project 🚀

Koishi 8x7b Qlora Gguf Parameters and Internals

Training Details 
Data Sources:
ewof/koishi-instruct-metharme
Methodology:
rank 16 qlora tune of mistralai/Mixtral-8x7B-v0.1 (all modules, merged)
Hardware Used:
4x nvidia a100 gpu cluster
Input Output 
Input Format:
Prompts using three different roles: `<|system|>`, `<|user|>` and `<|model|>`
LLM NameKoishi 8x7b Qlora Gguf
Repository 🤗https://huggingface.co/ewof/koishi-8x7b-qlora-gguf 
Required VRAM15.6 GB
Updated2026-04-27
Maintainerewof
Model Typemixtral
Instruction-BasedYes
Model Files  15.6 GB   20.4 GB   26.4 GB   26.4 GB   32.2 GB   32.2 GB   38.4 GB   49.6 GB
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typegguf|ggml|q2|q4_k|q5_k
Model ArchitectureAutoModel

Best Alternatives to Koishi 8x7b Qlora Gguf

Best Alternatives
Context / RAM
Downloads
Likes
...ixtral 8x7B Instruct V0.1 GGUF0K / 15.6 GB18053655
Dolphin 2.5 Mixtral 8x7b GGUF0K / 15.6 GB20494308
Dolphin 2.7 Mixtral 8x7b GGUF0K / 15.6 GB10801171
Phi 3 Mini 4K Instruct GGUF0K / 1.4 GB155417
Spydaz Web AI 0K / 4.4 GB1543
Autocomplete Model0K / 4.1 GB1020
Phi 3 Mini 4K Instruct0K / 2.3 GB400
...3 Mini 4k OLScience 4bitQ Gguf0K / 2.3 GB180
Dre Phi Gguf0K / 2.3 GB90
...i 3 Mini 4K Instruct V0.3 GGUF0K / 1.4 GB2275
Note: green Score (e.g. "73.2") means that the model is better than ewof/koishi-8x7b-qlora-gguf.

Rank the Koishi 8x7b Qlora Gguf Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 53972 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer