Autotrain compatible Base model:mistralai/codestral... Base model:quantized:mistralai... Code Gguf Mistral Q2 Quantized Region:us
Model Card on HF 🤗: https://huggingface.co/gaianet/Codestral-22B-v0.1-GGUF
Codestral 22B V0.1 GGUF 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)
Codestral 22B V0.1 GGUF Parameters and Internals
| Model Type |
| ||||||
| Additional Notes |
| ||||||
| Input Output |
|
| LLM Name | Codestral 22B V0.1 GGUF |
| Repository 🤗 | https://huggingface.co/gaianet/Codestral-22B-v0.1-GGUF |
| Model Name | Codestral-22B-v0.1 |
| Model Creator | mistralai |
| Base Model(s) | |
| Model Size | 22b |
| Required VRAM | 8.3 GB |
| Updated | 2025-02-05 |
| Maintainer | gaianet |
| Model Type | mistral |
| Model Files | |
| Supported Languages | code |
| GGUF Quantization | Yes |
| Quantization Type | gguf|q2|q4_k|q5_k |
| Model Architecture | MistralForCausalLM |
| License | MNPL-0.1 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.2 |
| Vocabulary Size | 32768 |
| Torch Data Type | bfloat16 |
Best Alternatives to Codestral 22B V0.1 GGUF
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Codestral 22B V0.1 GGUF | 32K / 8.3 GB | 250 | 1 |
| MwM 22B Instruct | 128K / 44.7 GB | 15 | 0 |
| ... Instruct 0.2 Chkpt 200 16 Bit | 128K / 44.7 GB | 20 | 1 |
| Mistral 22B V0.2 GGUF | 64K / 8.3 GB | 35 | 0 |
| ...l 22B V0.1 Hf FIM Fix Bnb 4bit | 32K / 13.1 GB | 5 | 1 |
| Text2cypher Codestral 16bit | 32K / 44.7 GB | 13 | 3 |
| ... Abliterated V3.8.0bpw H8 EXL2 | 32K / 21.2 GB | 7 | 1 |
| Codestral 22B V0.1 EXL2 8.0bpw | 32K / 20.9 GB | 9 | 3 |
| ...estral 22B V0.1 Hf 2 2bpw EXL2 | 32K / 6.6 GB | 8 | 1 |
| Codestral 22B V0.1 EXL2 6.0bpw | 32K / 16.9 GB | 7 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than gaianet/Codestral-22B-v0.1-GGUF .
Rank the Codestral 22B V0.1 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! 🌟
What open-source LLMs or SLMs are you in search of? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227