- 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
- 11 Dec 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-Instruct-v0.21.1M downloads in the last 30 days, 3.3k likes
Scores
Epoch's name: Mistral-7B-Instruct-v0.2. Best closed model on this set: Inflection-1, 89.7% (Inflection AI). All 136 results
- default setting35.4%Gemma: Open Models Based on Gemini Research and Technology
Epoch's name: Mistral-7B-Instruct-v0.2. Best closed model on this set: gpt-4-0314, 92.0% (OpenAI). All 170 results
Epoch's name: Mistral-7B-Instruct-v0.2. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results
Epoch's name: Mistral-7B-Instruct-v0.2. Best closed model on this set: gpt-4o-mini-2024-07-18, 88.7% (OpenAI). All 113 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-Instruct-v0.2), 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-Instruct-v0.2-GGUF (converted by TheBloke), 54k 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-Instruct-v0.2-GGUF:Q2_KOllama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q2_KDownload hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q2_K.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q3_K_S | 2.9 GBfile size | 4.4 GB2.9 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q3_K_SOllama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q3_K_SDownload hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q3_K_S.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q3_K_M | 3.3 GBfile size | 4.8 GB3.3 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q3_K_MOllama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q3_K_MDownload hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q3_K_M.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q3_K_L | 3.6 GBfile size | 5.1 GB3.6 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q3_K_LOllama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q3_K_LDownload hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q3_K_L.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q4_0 | 3.8 GBfile size | 5.3 GB3.8 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q4_0Ollama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q4_0Download hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q4_0.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q4_K_S | 3.9 GBfile size | 5.4 GB3.9 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q4_K_SOllama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q4_K_SDownload hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q4_K_S.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q4_K_M | 4.1 GBfile size | 5.6 GB4.1 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q4_K_MOllama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q4_K_MDownload hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q4_K_M.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q5_0 | 4.7 GBfile size | 6.2 GB4.7 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q5_0Ollama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q5_0Download hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q5_0.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q5_K_S | 4.7 GBfile size | 6.2 GB4.7 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q5_K_SOllama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q5_K_SDownload hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q5_K_S.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q5_K_M | 4.8 GBfile size | 6.3 GB4.8 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q5_K_MOllama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q5_K_MDownload hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q5_K_M.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q6_K | 5.5 GBfile size | 7.0 GB5.5 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q6_KOllama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q6_KDownload hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q6_K.gguf" --local-dir Mistral-7B-Instruct-v0.2-GGUF |
| Q8_0 | 7.2 GBfile size | 8.7 GB7.2 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q8_0Ollama ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF:Q8_0Download hf download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --include "mistral-7b-instruct-v0.2.Q8_0.gguf" --local-dir Mistral-7B-Instruct-v0.2-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-Instruct-v0.2 --local-dir Mistral-7B-Instruct-v0.2Other conversions (15; sizes not read)
- TheBloke/Mistral-7B-Instruct-v0.2-AWQ AWQ, 185k downloads
- mlc-ai/Mistral-7B-Instruct-v0.2-q4f16_1-MLC Other, 1.7k downloads
- TheBloke/Mistral-7B-Instruct-v0.2-GPTQ GPTQ, 827 downloads
- OpenVINO/Mistral-7B-Instruct-v0.2-int4-ov Other, int4, 150 downloads
- OpenVINO/Mistral-7B-Instruct-v0.2-int4-cw-ov Other, int4, 81 downloads
- OpenVINO/Mistral-7B-Instruct-v0.2-int8-ov Other, int8, 18 downloads
- MaziyarPanahi/Mistral-7B-Instruct-v0.2-AWQ AWQ, 12 downloads
- JongYeop/Mistral-7B-Instruct-v0.2-FP4-W4A4 NVFP4, 12 downloads
- solidrust/Mistral-7B-Instruct-v0.2-AWQ AWQ, 11 downloads
- liodon-ai/Mistral-7B-Instruct-v0.2-FP8 FP8, 11 downloads
- JongYeop/Mistral-7B-Instruct-v0.2-FP8-W8A8 FP8, 10 downloads
- LoneStriker/Mistral-7B-Instruct-v0.2-Neural-Story-AWQ AWQ, 9 downloads
- leliuga/mistral-7b-instruct-v0.2-bnb-4bit bitsandbytes, 4bit, 9 downloads
- 28Smiles/Mistral-7B-Instruct-v0.2-GPTQ GPTQ, 8 downloads
- AiAF/Mistral-7B-Instruct-v0.2_DPO-training-test bitsandbytes, 6 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.
- microsoft/Sentiment-Analysis-7B7.2B3.2kUnreviewed
- segolilylabs/Lily-Cybersecurity-7B-v0.27.2B328Unreviewed
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.