dolphin-2.9.1-yi-1.5-34b vs Qwen3-Next-80B-A3B-Instruct-FP8
Specs, VRAM requirements and download trends — updated 6 August 2026.
Qwen · B
Params
81.3 B
Context
262,144
30d
339 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | dolphin-2.9.1-yi-1.5-34b | Qwen3-Next-80B-A3B-Instruct-FP8 |
|---|---|---|
| Parameters | 34.4 B | 81.3 B |
| Architecture | LlamaForCausalLM | Qwen3NextForCausalLM |
| Context length | 8,192 | 262,144 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 4,620,525 | 339,404 |
| Downloads all time | 70.0 M | 2.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-05-18 | 2025-09-22 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
4.6 M331 K
dolphin-2.9.1-yi-1.5-34b
Qwen3-Next-80B-A3B-Instruct-FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
dolphin-2.9.1-yi-1.5-34b · fp16
81.3 GB / 24 GB
Qwen3-Next-80B-A3B-Instruct-FP8 · fp16 @ 256K ctx
481.1 GB / 24 GB