h2ovl-mississippi-800m vs TinyLlama-1.1B-Chat-v0.3-GPTQ
Specs, VRAM requirements and download trends — updated 7 August 2026.
h2oai · A · Open weights
Params
830 M
Context
—
30d
242 K
apache-2.0 · commercial OK
TheBloke · B · Open weights
Params
1.1 B
Context
2,048
30d
195 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | h2ovl-mississippi-800m | TinyLlama-1.1B-Chat-v0.3-GPTQ |
|---|---|---|
| Parameters | 830 M | 1.1 B |
| Architecture | H2OVLChatModel | LlamaForCausalLM |
| Context length | — | 2,048 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 241,743 | 194,649 |
| Downloads all time | 9.0 M | 6.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-10-16 | 2023-10-03 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.1 M195 K
h2ovl-mississippi-800m
TinyLlama-1.1B-Chat-v0.3-GPTQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
TinyLlama-1.1B-Chat-v0.3-GPTQ · fp16
1.5 GB / 24 GB
h2ovl-mississippi-800m · fp16
2.4 GB / 24 GB