Mistral-7B-Instruct-v0.1
- Out Output modalities: Text
- Open weights
Prices
1 offering · prices as listed@cf/mistral/mistral-7b-instruct-v0.1| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.11 | $0.19 |
Prices from Cloudflare Workers AI pricing (opens in a new tab) (checked Nov 1, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Licence
- apache-2.0
- Family
- mistral
- Model ID
Not stated on Mistral AI’s pages: max input, input modalities, reasoning, reasoning efforts, reasoning can be off, max thinking budget, tool use, structured output, built-in tools, knowledge cutoff, aliases.
Run locally
Weights: mistralai/Mistral-7B-Instruct-v0.1- Parameters 7.2B
- Dense
- Native precision BF16
- Layers 32
- KV cache per token 128 KB
- Config positions 32K (config.json max_position_embeddings)
- Needs
- ≈ 15.2 GB (weights 13.5 (maker’s file) + KV cache 1.0 + overhead 0.7)
- Usable
- 21.6 GB (90% of its memory)
- Generation speed
- 32–49 tok/s
- Longest context
- 32K (the model’s limit)
- First token
- about 0.23–0.35 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 13.5 GB | ≈ 15.2 | ●Runs well 32–49 tok/s | 32K |
| Q8_0 | 7.2 GB | ≈ 8.7 | ●Runs well 57–86 tok/s | 32K |
| FP8 | 6.7 GB | ≈ 8.2 | ●Runs well 61–91 tok/s | 32K |
| Q6_K | 5.5 GB | ≈ 7.0 | ●Runs well 72–108 tok/s | 32K |
| Q5_K_M | 4.8 GB | ≈ 6.3 | ●Runs well 81–121 tok/s | 32K |
| Q5_0 | 4.6 GB | ≈ 6.1 | ●Runs well 83–125 tok/s | 32K |
| Q4_K_M | 4.1 GB | ≈ 5.6 | ●Runs well 92–138 tok/s | 32K |
| Q4_0 | 3.8 GB | ≈ 5.3 | ●Runs well 98–147 tok/s | 32K |
| IQ4_XS | 3.6 GB | ≈ 5.1 | ●Runs well 102–154 tok/s | 32K |
| Q3_K_Mquality drops | 3.3 GB | ≈ 4.8 | ●Runs well 109–164 tok/s | 32K |
| IQ3_XXSquality drops | 2.6 GB | ≈ 4.1 | ●Runs well 131–197 tok/s | 32K |
| Q2_Kquality drops | 2.5 GB | ≈ 4.0 | ●Runs well 133–200 tok/s | 32K |
| IQ2_XXSquality drops | 1.7 GB | ≈ 3.2 | ●Runs well 172–257 tok/s | 32K |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): GPU GeForce RTX 3080; unified memory Apple M5 · 16 GB.
Run commands
vllm serve mistralai/Mistral-7B-Instruct-v0.1 --max-model-len 8192
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by usThis model isn’t on any leaderboard we cite yet.
Changes
All changes →- Now priced on Cloudflare Workers AI Input $0.11 · Output $0.19
Sources
- mistralai/Mistral-7B-Instruct-v0.1 model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- Cloudflare Workers AI pricing (opens in a new tab) developers.cloudflare.com · checked Nov 1, 2026
- mistralai/Mistral-7B-Instruct-v0.1 model card (opens in a new tab) huggingface.co · checked Nov 5, 2026
- mistralai/Mistral-7B-Instruct-v0.1 config.json (opens in a new tab) huggingface.co · checked Nov 4, 2026
- mistralai/Mistral-7B-Instruct-v0.1 files (opens in a new tab) huggingface.co · checked Nov 5, 2026
Mistral AI’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Mistral AI · France · mistral.ai
Related models
Snapshots, the same family and other models from this provider