Merged Model Arxiv:1910.09700 4-bit Autotrain compatible Awq Conversational Endpoints compatible Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/doubledsbv/KafkaLM-Mixtral-8x7B-V0.2_DPO-AWQ
KafkaLM Mixtral 8x7B V0.2 DPO AWQ Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
KafkaLM Mixtral 8x7B V0.2 DPO AWQ Parameters and Internals
| LLM Name | KafkaLM Mixtral 8x7B V0.2 DPO AWQ |
| Repository 🤗 | https://huggingface.co/doubledsbv/KafkaLM-Mixtral-8x7B-V0.2_DPO-AWQ |
| Merged Model | Yes |
| Model Size | 6.5b |
| Required VRAM | 24.7 GB |
| Updated | 2025-07-25 |
| Maintainer | doubledsbv |
| Model Type | mixtral |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MixtralForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to KafkaLM Mixtral 8x7B V0.2 DPO AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mixtral 8x7B Instruct V0.1 AWQ | 32K / 24.7 GB | 6 | 0 |
| Karakuri Lm 8x7b Chat V0.1 AWQ | 32K / 24.7 GB | 5 | 0 |
| Mixtral 8x7B Instruct V0.1 AWQ | 32K / 24.7 GB | 2586 | 58 |
| Taiwan LLM 8x7B DPO AWQ | 32K / 24.7 GB | 7 | 1 |
| Functionary Medium V2.4 AWQ | 32K / 24.7 GB | 5 | 3 |
| Dolphin 2.7 Mixtral 8x7b AWQ | 32K / 24.7 GB | 1590 | 23 |
| Mixtral Instruct AWQ | 32K / 24.7 GB | 1527 | 43 |
| H2ogpt Mixtral 8x7b 32K AWQ | 32K / 24.7 GB | 8 | 0 |
| Mixtral 8x7b V0.1 AWQ | 32K / 24.7 GB | 860 | 10 |
| Synatra Mixtral 8x7B AWQ | 32K / 24.7 GB | 4 | 3 |
Rank the KafkaLM Mixtral 8x7B V0.2 DPO AWQ 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! 🌟
What open-source LLMs or SLMs are you in search of? 50068 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124