DeepSeek-V3.2 vs DeepSeek-V3.2-AWQ
Specs, VRAM requirements and download trends — updated 14 August 2026.
deepseek-ai · A · Open weights
Params
685.4 B
Context
163,840
30d
7.6 M
mit · commercial OK
QuantTrio · B · Open weights
Params
685.4 B
Context
163,840
30d
168 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V3.2 | DeepSeek-V3.2-AWQ |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 685.4 B | 685.4 B |
| Architecture | DeepseekV32ForCausalLM | DeepseekV32ForCausalLM |
| Context length | 163,840 | 163,840 |
| Licence | mit | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 7,616,440 | 167,983 |
| Downloads all time | 35.7 M | 1.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-12-01 | 2025-12-03 |
| API input price / 1M tokens | $0.26 | not on OpenRouter |
| API output price / 1M tokens | $0.38 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.64 | not on OpenRouter |
| Cached input / 1M tokens | $0.13 | not on OpenRouter |
| AA Intelligence Index | — | not on OpenRouter |
| AA Coding Index | 44.2 | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 147,456 | not on OpenRouter |
| API providers | 7 | 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-V3.2
$0.64
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
7.6 M168 K
DeepSeek-V3.2
DeepSeek-V3.2-AWQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-V3.2-AWQ · fp16 @ 160K ctx
2,454.7 GB / 24 GB
DeepSeek-V3.2 · fp16 @ 160K ctx
2,815.1 GB / 24 GB