- Size
- 7.2B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
- On the Hub since
- 20 Sep 2023the date the repo was created
- Context length
- 32k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)MistralForCausalLM
- On Hugging Face
- mistralai/Mistral-7B-v0.1432k downloads in the last 30 days, 4.2k likes
Scores
- default setting47.1%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: gpt-3.5-turbo-1106, 58.1% (OpenAI). All 15 results
- Shots: 10-shot78.6%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Shots: 0-shot55.5%Nemotron-4 15B Technical Report
- Shots: 0-shot54.9%Mixtral of Experts
- default setting54.9%Gemma: Open Models Based on Gemini Research and Technology
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: gpt-3.5-turbo-1106, 87.4% (OpenAI). All 134 results
- default setting56.1%Gemma: Open Models Based on Gemini Research and Technology
- Shots: 339.5%Nemotron-4 15B Technical Report
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: gemini-1.5-pro-001, 89.2% (Google DeepMind). All 88 results
- Shots: 587.4%Stanford HELM
- Shots: 280.5%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: Inflection-1, 89.7% (Inflection AI). All 136 results
- Shots: 854.4%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Shots: 850.0%Mixtral of Experts
- default setting47.5%Yi: Open Foundation Models by 01.AI
- Shots: 538.1%Stanford HELM
- Shots: 835.4%Nemotron-4 15B Technical Report
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: gpt-4-0314, 92.0% (OpenAI). All 170 results
- default setting81.0%Mixtral of Experts
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: gpt-4-0314, 95.3% (OpenAI). All 113 results
- Shots: 562.5%Mixtral of Experts
- Shots: 561.7%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Shots: 560.1%Nemotron-4 15B Technical Report
- Shots: 556.6%Stanford CRFM Leaderboard
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: gpt-3.5-turbo-1106, 86.0% (OpenAI). All 70 results
- default setting83.0%Nemotron-4 15B Technical Report
- Shots: 573.4%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: gpt-4o-mini-2024-07-18, 88.7% (OpenAI). All 113 results
- Shots: 575.2%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Shots: 562.5%Gemma: Open Models Based on Gemini Research and Technology
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: claude-2.0, 87.5% (Anthropic). All 115 results
- Shots: 075.3%Training Compute-Optimal Large Language Models
- Shots: 075.3%Nemotron-4 15B Technical Report
- default setting74.2%Mixtral of Experts
- default setting74.2%Gemma: Open Models Based on Gemini Research and Technology
- Shots: 554.2%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: Mistral-7B-v0.1. Best closed model on this set: claude-3-opus-20240229, 88.5% (Anthropic). All 137 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 1.0 GB, worked out from the model's config (mistralai/Mistral-7B-v0.1), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
TheBloke/Mistral-7B-v0.1-GGUF (converted by TheBloke), 9.2k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 2.9 GBfile size | 4.4 GB2.9 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q2_KOllama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q2_KDownload hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q2_K.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q3_K_S | 2.9 GBfile size | 4.4 GB2.9 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q3_K_SOllama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q3_K_SDownload hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q3_K_S.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q3_K_M | 3.3 GBfile size | 4.8 GB3.3 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q3_K_MOllama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q3_K_MDownload hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q3_K_M.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q3_K_L | 3.6 GBfile size | 5.1 GB3.6 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q3_K_LOllama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q3_K_LDownload hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q3_K_L.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q4_0 | 3.8 GBfile size | 5.3 GB3.8 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q4_0Ollama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q4_0Download hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q4_0.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q4_K_S | 3.9 GBfile size | 5.4 GB3.9 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q4_K_SOllama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q4_K_SDownload hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q4_K_S.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q4_K_M | 4.1 GBfile size | 5.6 GB4.1 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q4_K_MOllama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q4_K_MDownload hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q4_K_M.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q5_0 | 4.7 GBfile size | 6.2 GB4.7 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q5_0Ollama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q5_0Download hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q5_0.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q5_K_S | 4.7 GBfile size | 6.2 GB4.7 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q5_K_SOllama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q5_K_SDownload hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q5_K_S.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q5_K_M | 4.8 GBfile size | 6.3 GB4.8 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q5_K_MOllama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q5_K_MDownload hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q5_K_M.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q6_K | 5.5 GBfile size | 7.0 GB5.5 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q6_KOllama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q6_KDownload hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q6_K.gguf" --local-dir Mistral-7B-v0.1-GGUF |
| Q8_0 | 7.2 GBfile size | 8.7 GB7.2 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q8_0Ollama ollama run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q8_0Download hf download TheBloke/Mistral-7B-v0.1-GGUF --include "mistral-7b-v0.1.Q8_0.gguf" --local-dir Mistral-7B-v0.1-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 13.5 GBfile size | 15.0 GB13.5 + 1.0 + 0.50 |
hf download mistralai/Mistral-7B-v0.1 --local-dir Mistral-7B-v0.1Other conversions (8; sizes not read)
- liodon-ai/Mistral-7B-v0.1-ONNX Other, 329 downloads
- TheBloke/Mistral-7B-v0.1-GPTQ GPTQ, 173 downloads
- TheBloke/Mistral-7B-v0.1-AWQ AWQ, 151 downloads
- amd/Mistral-7B-v0.1-FP8-KV FP8, 32 downloads
- iproskurina/Mistral-7B-v0.1-GPTQ-4bit-g128 GPTQ, 4bit, 23 downloads
- xHascox/Mistral-7B-v0.1-guanaco-m600 bitsandbytes, 23 downloads
- asya-ai/Mistral-7B-v0.1-AWQ AWQ, 18 downloads
- amd/Mistral-7B-v0.1-w4a16-tao-symgroup-torchao-v0.17.0 Other, w4a16, 17 downloads
The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- mistralai/Mistral-7B-Instruct-v0.17.2B119kReviewed
- HuggingFaceH4/zephyr-7b-beta7.2B48kUnreviewed
- openchat/openchat-3.5-01067.2B12kUnreviewed
- nvidia/OpenMath-Mistral-7B-v0.1-hf7.2B247Unreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.