Qwen3.6-35B-A3B-NVFP4 vs Llama-3.1-8B-Instruct
Specs, VRAM requirements and download trends — updated 10 November 2026.
nvidia · A · Open weights
Params
18.7 B
Context
—
30d
4.0 M
apache-2.0 · commercial OK
meta-llama · B · Open weights
Params
8.0 B
Context
—
30d
4.5 M
llama3.1 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | Llama-3.1-8B-Instruct |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 18.7 B | 8.0 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | LlamaForCausalLM |
| Context length | — | 131,072 |
| Licence | apache-2.0 | llama3.1 |
| Commercial use | Allowed | Conditional |
| Languages | — | 8 |
| Downloads 30d | 3,971,809 | 4,504,499 |
| Downloads all time | 42.1 M | 193.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2026-05-27 | 2024-07-18 |
| API input price / 1M tokens | not on OpenRouter | $0.02 |
| API output price / 1M tokens | not on OpenRouter | $0.04 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.06 |
| Cached input / 1M tokens | not on OpenRouter | — |
| AA Intelligence Index | not on OpenRouter | — |
| AA Coding Index | not on OpenRouter | 5.4 |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 16,384 |
| API providers | not on OpenRouter | 4 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Llama-3.1-8B-Instruct
$0.06
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
12.6 M3.8 M
Qwen3.6-35B-A3B-NVFP4
Llama-3.1-8B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.1-8B-Instruct · fp16
19.4 GB / 24 GB
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB