Mistral 7B v0.1
Sep 2023
Mistral 7B v0.1Compare inonMMLU-Pro · Official board
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGPT OSS 20BmediumOpen×2.4-93%$0.018 / $0.09Memory (4-bit): 3.6 GB → 13 GB
BetterGemini 3.1 Prounstated×3+800%$2 / $12OpenGemma 2 9B It+69%-93%$0.03 / $0.06Context: 33K → 8K+1
CheaperQwQ 32BOpen×2.2-57%$0.15 / $0.40Memory (4-bit): 3.6 GB → 20 GB
CheaperLlama 3.3 70B InstructunstatedOpen×2.1-69%$0.10 / $0.32Memory (4-bit): 3.6 GB → 42 GBModelScoreCostPer taskWhat changes
GPT OSS 20BmediumOpen×2.4-93%$0.018 / $0.09Memory (4-bit): 3.6 GB → 13 GBQwQ 32BOpen×2.2-57%$0.15 / $0.40Memory (4-bit): 3.6 GB → 20 GBLlama 3.3 70B InstructunstatedOpen×2.1-69%$0.10 / $0.32Memory (4-bit): 3.6 GB → 42 GBGPT-4o Miniunstated×2-48%$0.15 / $0.60Llama 3.1 70B InstructunstatedOpen×2-20%$0.40 / $0.40Memory (4-bit): 3.6 GB → 42 GBModelScoreCostPer taskWhat changes
Gemini 3.1 Prounstated×3+800%$2 / $12GPT-4ounstated×2.4+775%$2.50 / $10GPT OSS 20BmediumOpen×2.4-93%$0.018 / $0.09Memory (4-bit): 3.6 GB → 13 GBQwQ 32BOpen×2.2-57%$0.15 / $0.40Memory (4-bit): 3.6 GB → 20 GBLlama 3.3 70B InstructunstatedOpen×2.1-69%$0.10 / $0.32Memory (4-bit): 3.6 GB → 42 GBModelScoreCostPer taskWhat changes
Gemma 2 9B ItOpen+69%-93%$0.03 / $0.06Context: 33K → 8K+1
Phi 3.5 Mini InstructOpen+55%——Qwen 2 7B InstructOpen+53%-89%$0.055 / $0.055Memory (4-bit): 3.6 GB → 3.8 GBLEXAONE 3.5 7.8B InstructOpen+50%——Memory (4-bit): 3.6 GB → 3.9 GBMistral NemounstatedOpen+45%-70%$0.15 / $0.15Memory (4-bit): 3.6 GB → 6.1 GBModelScoreCostPer taskWhat changes
Mixtral 8x22B InstructunstatedOpen+82%—$2 / $6Memory (4-bit): 3.6 GB → 84 GBMistral NemounstatedOpen+45%—$0.15 / $0.15Memory (4-bit): 3.6 GB → 6.1 GBMixtral 8x7B Instruct v0.1Open+40%—$0.54 / $0.54Memory (4-bit): 3.6 GB → 28 GBMistral 7B Instruct v0.2Opensame—$0.055 / $0.055No strict JSONMistral 7B Instruct v0.1Open-17%—$0.055 / $0.055Mistral 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
Benchmarks
in Chat & KnowledgeMMLU-Pro · official board30.9#29
FAQ
How much does Mistral 7B v0.1 cost?›
$0.40 per 1M input tokens and $0.80 per 1M output tokens (cheapest host: Featherless).
Is Mistral 7B v0.1 free to use?›
There is no free API; the cheapest paid price is $0.40 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Mistral 7B v0.1, and what is it best at?›
#29 of 32 in Chat & Knowledge.
Is Mistral 7B v0.1 better than Aya Expanse 8B?›
On MMLU-Pro · official board, Mistral 7B v0.1 scores 30.9 vs 33.7 — lower.
How can I use Mistral 7B v0.1?›
Through the Mistral API.
What is the context window of Mistral 7B v0.1?›
33K tokens.
When was Mistral 7B v0.1 released? Is there a newer version?›
Released 2023-09-20. It is the current version in its line.
Is Mistral 7B v0.1 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Mistral 7B v0.1 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Mistral 7B v0.1 read images?›
No, it accepts text only.
What is Mistral 7B v0.1?›
Mistral 7B v0.1 is an open-weights language model from Mistral, released Sep 2023.
What are the best alternatives to Mistral 7B v0.1?›
GPT OSS 20B (cheaper), Gemini 3.1 Pro (better), Gemma 2 9B It (open weights).