DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
Context window on the 2026-08-19 OpenRouter row: 131,072 tokens.
Max completion tokens on that row: 16,384.
Input / output on that row: $1.00 / $1.00 per 1M tokens.
Architecture fields: text->text · Llama3 · chatml.
Hugging Face id on that row: NousResearch/Hermes-3-Llama-3.1-405B.
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements
When you want the 2024-08-16 catalog SKU, not a later rename.
No independent board lists this exact SKU as of 2026-08-19.
No other card from this lab carries an independent board row either, so there is no sibling worth pointing at.
Boards checked: DeepSWE official (2026-08-13), Artificial Analysis Intelligence Index, vals.ai hero index. Every card that does carry a row is on the coding leaderboard.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
No Intelligence Index integer fetched for this identity. Chip omitted.
We did not open a vals.ai card for this identity. Chip omitted.
Plus is $25/mo with $25 weekly hosted usage. The Mac app stays free with your own keys. Get Plus is not Download for Mac.
Official weights id on the 2026-08-19 OpenRouter row: NousResearch/Hermes-3-Llama-3.1-405B. Community GGUF is a quant, not a second Continuum card.
This is the model repo, not Download for Mac. Downloads and likes from the Hugging Face API on 2026-08-19.
usedStorage and the sum of .safetensors sizes can differ (LFS pointers, non-shard files, duplicate copies). Cited separately. Source: recursive tree API, 2026-08-19.
| Path | Bytes |
|---|---|
model-00001-of-00191.safetensors | 4,806,672,880 |
model-00002-of-00191.safetensors | 4,026,532,224 |
model-00003-of-00191.safetensors | 4,630,578,112 |
model-00004-of-00191.safetensors | 4,630,578,112 |
model-00005-of-00191.safetensors | 3,489,661,192 |
model-00006-of-00191.safetensors | 4,630,578,112 |
model-00007-of-00191.safetensors | 4,630,578,112 |
model-00008-of-00191.safetensors | 3,489,661,192 |
model-00009-of-00191.safetensors | 4,630,578,112 |
model-00010-of-00191.safetensors | 4,630,578,112 |
model-00011-of-00191.safetensors | 3,489,661,192 |
model-00012-of-00191.safetensors | 4,630,578,112 |
model-00013-of-00191.safetensors | 4,630,578,112 |
model-00014-of-00191.safetensors | 3,489,661,192 |
model-00015-of-00191.safetensors | 4,630,578,112 |
model-00016-of-00191.safetensors | 4,630,578,120 |
model-00017-of-00191.safetensors | 3,489,661,192 |
model-00018-of-00191.safetensors | 4,630,578,120 |
model-00019-of-00191.safetensors | 4,630,578,120 |
model-00020-of-00191.safetensors | 3,489,661,192 |
model-00021-of-00191.safetensors | 4,630,578,120 |
model-00022-of-00191.safetensors | 4,630,578,120 |
model-00023-of-00191.safetensors | 3,489,661,192 |
model-00024-of-00191.safetensors | 4,630,578,120 |
model-00025-of-00191.safetensors | 4,630,578,120 |
model-00026-of-00191.safetensors | 3,489,661,192 |
model-00027-of-00191.safetensors | 4,630,578,120 |
model-00028-of-00191.safetensors | 4,630,578,120 |
model-00029-of-00191.safetensors | 3,489,661,192 |
model-00030-of-00191.safetensors | 4,630,578,120 |
model-00031-of-00191.safetensors | 4,630,578,120 |
model-00032-of-00191.safetensors | 3,489,661,192 |
model-00033-of-00191.safetensors | 4,630,578,120 |
model-00034-of-00191.safetensors | 4,630,578,120 |
model-00035-of-00191.safetensors | 3,489,661,192 |
model-00036-of-00191.safetensors | 4,630,578,120 |
model-00037-of-00191.safetensors | 4,630,578,120 |
model-00038-of-00191.safetensors | 3,489,661,192 |
model-00039-of-00191.safetensors | 4,630,578,120 |
model-00040-of-00191.safetensors | 4,630,578,120 |
model-00041-of-00191.safetensors | 3,489,661,192 |
model-00042-of-00191.safetensors | 4,630,578,120 |
model-00043-of-00191.safetensors | 4,630,578,120 |
model-00044-of-00191.safetensors | 3,489,661,192 |
model-00045-of-00191.safetensors | 4,630,578,120 |
model-00046-of-00191.safetensors | 4,630,578,120 |
model-00047-of-00191.safetensors | 3,489,661,192 |
model-00048-of-00191.safetensors | 4,630,578,120 |
model-00049-of-00191.safetensors | 4,630,578,120 |
model-00050-of-00191.safetensors | 3,489,661,192 |
model-00051-of-00191.safetensors | 4,630,578,120 |
model-00052-of-00191.safetensors | 4,630,578,120 |
model-00053-of-00191.safetensors | 3,489,661,192 |
model-00054-of-00191.safetensors | 4,630,578,120 |
model-00055-of-00191.safetensors | 4,630,578,120 |
model-00056-of-00191.safetensors | 3,489,661,192 |
model-00057-of-00191.safetensors | 4,630,578,120 |
model-00058-of-00191.safetensors | 4,630,578,120 |
model-00059-of-00191.safetensors | 3,489,661,192 |
model-00060-of-00191.safetensors | 4,630,578,120 |
model-00061-of-00191.safetensors | 4,630,578,120 |
model-00062-of-00191.safetensors | 3,489,661,192 |
model-00063-of-00191.safetensors | 4,630,578,120 |
model-00064-of-00191.safetensors | 4,630,578,120 |
tokenizer.json | 9,085,140 |
model.safetensors.index.json | 94,027 |
tokenizer_config.json | 55,808 |
README.md | 12,554 |
.gitattributes | 1,519 |
config.json | 888 |
special_tokens_map.json | 444 |
generation_config.json | 147 |
Showing the first 64 of 191 safetensor shards, plus 8 other files. The snapshot was capped at 64 shards when the tree API was read on 2026-08-19, so the remaining 127 are on the Files tab, not on this page. Totals above are the full tree API sum, not this slice. Byte sizes are Hub tree API size fields, never invented.
OpenRouter slug nousresearch/hermes-3-llama-3.1-405b on the 2026-08-19 catalog.
First party: https://nousresearch.com/.
Not on the Continuum host list fetched 2026-08-19.
We list first-party and OpenRouter, plus Continuum only when the live public allowlist named the id. This is not a 15-host routing table.
OpenRouter 2026-08-19: $1.00 in / $1.00 out per 1M tokens. Context 131,072 in / 16,384 out.
No separate internal-reasoning price on that row.
| Claim | Source | As of |
|---|---|---|
| OpenRouter id nousresearch/hermes-3-llama-3.1-405b; context 131072; created 1723766400; $1.00 / $1.00 per 1M | OpenRouter /api/v1/models | 2026-08-19 |
| OpenRouter id nousresearch/hermes-3-llama-3.1-405b, context 131,072 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 611 | Hugging Face API NousResearch/Hermes-3-Llama-3.1-405B | 2026-08-19 |
| HF safetensors.total: 405,853,388,800 stored tensors; HF API usedStorage 811,706,916,800 bytes; created 2024-08-13T04:57:53.000Z; HF tensors BF16 | Hugging Face API NousResearch/Hermes-3-Llama-3.1-405B | 2026-08-19 |
| 191 safetensor shards; shard bytes 811,706,916,800; tree files 199 | Hugging Face tree API NousResearch/Hermes-3-Llama-3.1-405B | 2026-08-19 |
No other card in this cluster shares a published DeepSWE official row we can put next to this one. We will not compare on vendor-blog numbers.
Continue through Nous Research's model family with Hermes 4.
Lab posts pick a harness, an effort, a split, and sometimes a private eval set. DeepSWE publishes the official mini-swe-agent row with cost, tokens, and steps. Scale SWE-bench Pro only counts when the public shared-harness board has a row we can fetch. A higher lab number is usually a different test, not a better one.
No Continuum hosted id is verified for this model, so this page does not invent a curl target. Use the first-party API or the OpenRouter slug nousresearch/hermes-3-llama-3.1-405b.