Updated 18 min ago · first seen 11 Sept 2026
model_01M294ZKJ7C4DTV61XP2BHQ8WH
- Parameters
- 70.5B
- T2 · 2 h ago
- Context
- 128K tokens
- T2 · 29 min ago
- Released
- 18 Aug 2025
- T2 · 1 h ago
- License
- llama3
- T2 · 1 h ago
Specification
- Release date
- 18 Aug 2025
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- License
- llama3
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Architecture
- LlamaForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Parameters
- 70.5B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Context window
- 128K tokens
Source:Artificial AnalysisT2observed 29 min agomedium
- Languages
- en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Base model
- meta-llama/Meta-Llama-3.1-70B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 43 min agomedium
- File size
- 141.1 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Hugging Face repo
- NousResearch/Hermes-4-70B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads
- 7,925
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 18 min agomedium
- Likes
- 216
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 18 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Hf inference providers
- featherless-ai
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Last modified
- 2025-09-02T06:40:36+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Downloads all time
- 58,525
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Model type
- llama
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Tags
- transformers, safetensors, llama, text-generation, Llama-3.1, instruct, finetune, reasoning, hybrid-mode, chatml, function calling, tool use, json mode, structured outputs, atropos, dataforge, long context, roleplaying, chat, en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Weights dtype
- BF16
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
23
Source tiers
T223
Freshest observation
18 min ago
Conflicts
None
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Yes
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 128K tokens
Source:Artificial AnalysisT2observed 29 min agomedium
- Languages
- en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 22.51% | pass^1 | aa_slug=hermes-4-llama-3-1-70b-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 7.91 | index | aa_slug=hermes-4-llama-3-1-70b-reasoning · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 69.9% | accuracy | aa_slug=hermes-4-llama-3-1-70b-reasoning · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 8.76% | accuracy | aa_slug=hermes-4-llama-3-1-70b-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 31.29% | accuracy | aa_slug=hermes-4-llama-3-1-70b-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 4.55% | accuracy | aa_slug=hermes-4-llama-3-1-70b-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
No current prices recorded
Price history
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 41.1 GB | Yes |
| Apple M3 Ultra | 4bit | — | 41.1 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 41.1 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 41.1 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 41.1 GB | Yes |
| Apple M2 Ultra | 4bit | — | 41.1 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 41.1 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 41.1 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 41.1 GB | Yes |
| Apple M1 Ultra | 4bit | — | 41.1 GB | Yes |
| Apple M3 Max | 4bit | — | 41.1 GB | Yes |
| Apple M4 Max | 4bit | — | 41.1 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 41.1 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 41.1 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 41.1 GB | Yes |
| Apple M2 Max | 4bit | — | 41.1 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 41.1 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 41.1 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 41.1 GB | Yes |
| Apple M1 Max | 4bit | — | 41.1 GB | Yes |
| Apple M4 Pro | 4bit | — | 41.1 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 41.1 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 41.1 GB | Yes |
| Apple M3 Pro | 4bit | — | 41.1 GB | No |
| Apple M1 Pro | 4bit | — | 41.1 GB | No |
| Apple M2 Pro | 4bit | — | 41.1 GB | No |
| Apple M4 | 4bit | — | 41.1 GB | No |
| iMac (Apple M4) | 4bit | — | 41.1 GB | No |
| Mac mini (Apple M6) | 4bit | — | 41.1 GB | No |
| MacBook Air (Apple M5) | 4bit | — | 41.1 GB | No |
| MacBook Pro (Apple M5) | 4bit | — | 41.1 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 41.1 GB | No |
| Apple M2 | 4bit | — | 41.1 GB | No |
| Apple M3 | 4bit | — | 41.1 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 41.1 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 41.1 GB | No |
| Apple M1 | 4bit | — | 41.1 GB | No |
Ancestors 2
- Llama-3.1-70BMeta AI
- Meta-Llama-3.1-70BMeta AI
This model
Hermes-4-70B
70.5B params
Quantizations 0
None recorded.
Descendants 0
None recorded.
Papers 1
- arXiv:2508.18255Active35
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Hugging Face repo
Hugging Face repohf_repo1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| NousResearch/Hermes-4-70B | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Hermes-4-70B scores 4.55% on Terminal-Bench
artificial_analysisHermes-4-70B scores 22.51% on τ²-bench
artificial_analysisHermes-4-70B scores 31.29% on IFBench
artificial_analysisHermes-4-70B scores 8.76% on Humanity's Last Exam
artificial_analysisHermes-4-70B scores 7.91 on Artificial Analysis Intelligence Index
artificial_analysisHermes-4-70B: base model changed from ["meta-llama/Llama-3.1-70B", "meta-llama/Meta-Llama-3.1-7… to ["meta-llama/Meta-Llama-3.1-70B"]
Base modelmeta-llama/Llama-3.1-70B, meta-llama/Meta-Llama-3.1-70B→meta-llama/Meta-Llama-3.1-70Bhuggingface
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=NousResearch&p=0&sort=downloads | listing | T2· Quality secondary | 18 min ago | 3 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 29 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/NousResearch/Hermes-4-70B/raw/main/README.md | model_card | T2· Quality secondary | 42 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/NousResearch/Hermes-4-70B | model_page | T2· Quality secondary | 1 h ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.