DeepSeek-V4-Flash vs Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata
Specs, VRAM requirements and download trends — updated 25 October 2026.
deepseek-ai · A · Open weights
Params
158.1 B
Context
1,048,576
30d
880 K
mit · commercial OK
Maximilian228 · B · Open weights
Params
180.0 B
Context
—
30d
245 K
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash | Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 158.1 B | 180.0 B |
| Architecture | DeepseekV4ForCausalLM | — |
| Context length | 1,048,576 | — |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 2 |
| Downloads 30d | 880,327 | 244,900 |
| Downloads all time | 13.0 M | 245 K |
| Quantizations on the Hub | SAFETENSORS | GGUF |
| Gated | No | No |
| First seen on the Hub | 2026-04-22 | 2026-10-09 |
| API input price / 1M tokens | $0.091 | not on OpenRouter |
| API output price / 1M tokens | $0.18 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.27 | not on OpenRouter |
| Cached input / 1M tokens | $0.018 | not on OpenRouter |
| AA Intelligence Index | 24.4 | not on OpenRouter |
| AA Coding Index | 52 | not on OpenRouter |
| AA Agentic Index | 26.3 | not on OpenRouter |
| Max output tokens | 943,717 | not on OpenRouter |
| API providers | 15 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V4-Flash
$0.27
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
3.1 M146 K
DeepSeek-V4-Flash
Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-V4-Flash · fp16 @ 1024K ctx
3,211.0 GB / 24 GB