Qwen3.6-35B-A3B-NVFP4 vs Hermes-3-Llama-3.1-70B
Specs, VRAM requirements and download trends — updated 24 October 2026.
nvidia · A · Open weights
Params
18.7 B
Context
—
30d
4.1 M
apache-2.0 · commercial OK
NousResearch · B · Open weights
Params
70.6 B
Context
131,072
30d
2 K
llama3 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | Hermes-3-Llama-3.1-70B |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 18.7 B | 70.6 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | LlamaForCausalLM |
| Context length | — | 131,072 |
| Licence | apache-2.0 | llama3 |
| Commercial use | Allowed | Conditional |
| Languages | — | 1 |
| Downloads 30d | 4,104,529 | 2,075 |
| Downloads all time | 39.4 M | 334 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2024-07-29 |
| API input price / 1M tokens | not on OpenRouter | $0.70 |
| API output price / 1M tokens | not on OpenRouter | $0.70 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $1.40 |
| Cached input / 1M tokens | not on OpenRouter | — |
| AA Intelligence Index | not on OpenRouter | 6.7 |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 16,384 |
| API providers | not on OpenRouter | 1 |
| Tool calling | not on OpenRouter | No |
| Reasoning mode | not on OpenRouter | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Hermes-3-Llama-3.1-70B
$1.40
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
12.6 M2 K
Qwen3.6-35B-A3B-NVFP4
Hermes-3-Llama-3.1-70B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB
Hermes-3-Llama-3.1-70B · fp16 @ 128K ctx
325.0 GB / 24 GB