dolphin-2.9.1-yi-1.5-34b vs Meta-Llama-3.1-70B-Instruct-AWQ-INT4
Specs, VRAM requirements and download trends — updated 25 October 2026.
dphn · A · Open weights
Params
34.4 B
Context
8,192
30d
4.6 M
apache-2.0 · commercial OK
hugging-quants · B · Open weights
Params
70.6 B
Context
131,072
30d
140 K
llama3.1 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | dolphin-2.9.1-yi-1.5-34b | Meta-Llama-3.1-70B-Instruct-AWQ-INT4 |
|---|---|---|
| Parameters | 34.4 B | 70.6 B |
| Architecture | LlamaForCausalLM | LlamaForCausalLM |
| Context length | 8,192 | 131,072 |
| Licence | apache-2.0 | llama3.1 |
| Commercial use | Allowed | Conditional |
| Languages | — | 8 |
| Downloads 30d | 4,606,431 | 140,116 |
| Downloads all time | 83.2 M | 5.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-05-18 | 2024-07-19 |
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
4.8 M140 K
dolphin-2.9.1-yi-1.5-34b
Meta-Llama-3.1-70B-Instruct-AWQ-INT4
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
Meta-Llama-3.1-70B-Instruct-AWQ-INT4 · fp16 @ 128K ctx
213.6 GB / 24 GB