n

Hermes 3 70B Instruct

Aug 2024
nHermes 3 70B Instruct
Compare in
on
—per task?
$0.70 / $0.70per 1M in / out?
30 tok/sfirst token in 2.4 s?
128Kcontext

Ranking?

Strong at

C
Reasoning#309 of 334Science#279 of 312

Alternatives?

ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 ProthinkingOpen×7.7-22%$0.13Memory (4-bit): 42 GB → 615 GB+4BetterGPT-6 Lunalow×3.6-71%$0.005Function calling only with none · Chat Completions+3OpenQwen3.8 27Bxhigh×5.6+37%$1.01max_tokens range · QwenCloud+4CheaperDeepSeek V4.1 Flash 1017maxOpen×7.5-25%$0.26Memory (4-bit): 42 GB → 458 GB+5CheaperClaude Haiku 5.5max×7.2-71%$0.21Remove sampling parameters+5

Run it yourself

estimate
Fits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✓ 48 GB GPU · compressed✓ 80 GB GPU · 8-bit
LicenceLlama 3 licencecommercial use with conditions

Benchmarks

all categories
Chat & Knowledge
Humanity's Last Exam4#312
AA Intelligence Index 4.3.2≈6#296
GPQA Diamond40.1#282
Coding
LiveCodeBench · AA archived18.8#136

FAQ

How much does Hermes 3 70B Instruct cost?›

$0.70 per 1M input tokens and $0.70 per 1M output tokens (cheapest host: DeepInfra).

Is Hermes 3 70B Instruct free to use?›

There is no free API; the cheapest paid price is $0.70 per 1M input tokens. The weights are open, so you can run it yourself.

How good is Hermes 3 70B Instruct, and what is it best at?›

#309 of 334 in Chat & Knowledge, #135 of 152 in Coding.

Is Hermes 3 70B Instruct better than Qwen3 Omni 30B A3B Instruct?›

On AA Intelligence Index 4.3.2, Hermes 3 70B Instruct scores 6 vs 6 — about the same.

How can I use Hermes 3 70B Instruct?›

Through the API of DeepInfra, Featherless.

What is the context window of Hermes 3 70B Instruct?›

128K tokens, with up to 16K output tokens.

When was Hermes 3 70B Instruct released? Is there a newer version?›

Released 2024-08-15. It has been superseded by Hermes 4 - Llama-3.1 70B.

Is Hermes 3 70B Instruct open source?›

Yes, the weights are open (llama3 licence).

Can I run Hermes 3 70B Instruct locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can Hermes 3 70B Instruct read images?›

No, it accepts text only.

What is Hermes 3 70B Instruct?›

Hermes 3 70B Instruct is an open-weights language model from nousresearch, released Aug 2024.

What are the best alternatives to Hermes 3 70B Instruct?›

MiMo v2.6 Pro (cheaper), GPT-6 Luna (better), Qwen3.8 27B (open weights).