Mistral 7B Instruct v0.1
Sep 2023
Mistral 7B Instruct v0.1Compare inonMMLU-Pro · Official board
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGPT OSS 20BmediumOpen×2.8-35%$0.018 / $0.09Memory (4-bit): 3.6 GB → 13 GB
BetterGemini 3.1 Prounstated×3.5+8,082%$2 / $12OpenGemma 2 9B It×2-32%$0.03 / $0.06Context: 33K → 8K+1
CheaperLlama 3.1 8B InstructunstatedOpen+72%-55%$0.02 / $0.04Memory (4-bit): 3.6 GB → 4 GBBetterGPT-4ounstated×2.9+7,855%$2.50 / $10ModelScoreCostPer taskWhat changes
GPT OSS 20BmediumOpen×2.8-35%$0.018 / $0.09Memory (4-bit): 3.6 GB → 13 GBGemma 2 9B ItOpen×2-32%$0.03 / $0.06Context: 33K → 8K+1Llama 3.1 8B InstructunstatedOpen+72%-55%$0.02 / $0.04Memory (4-bit): 3.6 GB → 4 GBModelScoreCostPer taskWhat changes
Gemini 3.1 Prounstated×3.5+8,082%$2 / $12GPT-4ounstated×2.9+7,855%$2.50 / $10GPT OSS 20BmediumOpen×2.8-35%$0.018 / $0.09Memory (4-bit): 3.6 GB → 13 GB
QwQ 32BOpen×2.7+286%$0.15 / $0.40Memory (4-bit): 3.6 GB → 20 GBLlama 3.3 70B InstructunstatedOpen×2.6+182%$0.10 / $0.32Memory (4-bit): 3.6 GB → 42 GBModelScoreCostPer taskWhat changes
Gemma 2 9B ItOpen×2-32%$0.03 / $0.06Context: 33K → 8K+1
Phi 3.5 Mini InstructOpen+86%——Qwen 2 7B InstructOpen+83%same$0.055 / $0.055Memory (4-bit): 3.6 GB → 3.8 GBLEXAONE 3.5 7.8B InstructOpen+80%——Memory (4-bit): 3.6 GB → 3.9 GBMistral NemounstatedOpen+74%+173%$0.15 / $0.15Memory (4-bit): 3.6 GB → 6.1 GBModelScoreCostPer taskWhat changes
Mixtral 8x22B InstructunstatedOpen×2.2—$2 / $6Memory (4-bit): 3.6 GB → 84 GBMistral NemounstatedOpen+74%—$0.15 / $0.15Memory (4-bit): 3.6 GB → 6.1 GBMixtral 8x7B Instruct v0.1Open+68%—$0.54 / $0.54Memory (4-bit): 3.6 GB → 28 GBMistral 7B v0.1Open+20%—$0.40 / $0.80Mistral 7B Instruct v0.2Open+20%—$0.055 / $0.055No strict JSONMistral Large 4thinkingn/a—$1.13Infinite whitespace stream+4Mistral Medium 3.5highOpenn/a—$0.50Memory (4-bit): 3.6 GB → 77 GBMistral Small 4thinkingOpenn/a—$0.015Memory (4-bit): 3.6 GB → 72 GBAll Mistral models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
History
4 versionsBenchmarks
in Chat & KnowledgeMMLU-Pro · official board25.8#31
FAQ
How much does Mistral 7B Instruct v0.1 cost?›
$0.055 per 1M input tokens and $0.055 per 1M output tokens (cheapest host: DeepInfra).
Is Mistral 7B Instruct v0.1 free to use?›
There is no free API; the cheapest paid price is $0.055 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Mistral 7B Instruct v0.1, and what is it best at?›
#31 of 32 in Chat & Knowledge.
Is Mistral 7B Instruct v0.1 better than Mistral 7B Instruct v0.2?›
On MMLU-Pro · official board, Mistral 7B Instruct v0.1 scores 25.8 vs 30.8 — lower.
How can I use Mistral 7B Instruct v0.1?›
Through the API of DeepInfra.
What is the context window of Mistral 7B Instruct v0.1?›
33K tokens.
When was Mistral 7B Instruct v0.1 released? Is there a newer version?›
Released 2023-09-27. It is the current version in its line.
Is Mistral 7B Instruct v0.1 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Mistral 7B Instruct v0.1 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Mistral 7B Instruct v0.1 read images?›
No, it accepts text only.
What is Mistral 7B Instruct v0.1?›
Mistral 7B Instruct v0.1 is an open-weights language model from Mistral, released Sep 2023.
What are the best alternatives to Mistral 7B Instruct v0.1?›
GPT OSS 20B (cheaper), Gemini 3.1 Pro (better), Gemma 2 9B It (open weights).