dolphin-2.9.1-yi-1.5-34b vs llm-jp-4-33b-thinking-gguf
Specs, VRAM requirements and download trends — updated 24 October 2026.
dphn · A · Open weights
Params
34.4 B
Context
8,192
30d
4.5 M
apache-2.0 · commercial OK
llm-jp · B · Open weights
Params
33.0 B
Context
—
30d
271 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | dolphin-2.9.1-yi-1.5-34b | llm-jp-4-33b-thinking-gguf |
|---|---|---|
| Parameters | 34.4 B | 33.0 B |
| Architecture | LlamaForCausalLM | — |
| Context length | 8,192 | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 2 |
| Downloads 30d | 4,537,444 | 271,493 |
| Downloads all time | 82.9 M | 498 K |
| Quantizations on the Hub | SAFETENSORS | GGUF |
| Gated | No | No |
| First seen on the Hub | 2024-05-18 | 2026-08-18 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
4.8 M192 K
dolphin-2.9.1-yi-1.5-34b
llm-jp-4-33b-thinking-gguf
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
llm-jp-4-33b-thinking-gguf · Q4_K_M
27.6 GB / 24 GB
dolphin-2.9.1-yi-1.5-34b · fp16
81.3 GB / 24 GB