---

license: apache-2.0

base_model: h2oai/h2ovl-mississippi-2b

tags: [gguf, crispembed, ocr, vlm]

---

h2ovl-mississippi-2b — CrispEmbed GGUF

H2OVL-Mississippi-2B for CrispEmbed.

Needs MSAC two-scale tiling and the h2ogpt2 prompt template (no BOS) — all

handled by the runtime.

crispembed -m h2ovl-mississippi-2b-q8_0.gguf --ocr page.png

| file | size | verdict |

|---|--:|---|

| h2ovl-mississippi-2b-f16.gguf | 4636 MB | reference precision |

| h2ovl-mississippi-2b-q8_0.gguf | 2592 MB | recommended — vision tower held at F16 |

| ~~q4_k~~ | — | withdrawn, measured broken |

Parity

Per-stage against a reference dumped from the Python blueprint

(internvl2/h2ovl-mississippi-2b/ref.gguf in

cstr/crispembed-regression-fixtures),

CPU backend, plus the decoded output on a full scanned page:

| stage | f16 | q8_0 (shipped) | q4_k |

|---|--:|--:|--:|

| vis_proj_output | 0.999974 | 0.999974 | 0.912992 |

| vis_pixel_unshuffle | 0.999691 | 0.999691 | 0.380373 |

| llm_layer_0 | 1.000000 | 0.982747 | 0.594995 |

| llm_layer_3 | 1.000000 | 0.962142 | −0.279113 |

| decoded page | transcribes | transcribes | fluent but wrong |

The shipped q8_0 keeps the vision tower at F16 — that costs ~13 % size and

lifts every vision stage to the f16 ceiling. The InternViT encoder is 24

residual blocks, so per-weight error compounds: at Q8_0 the tower drifts to 0.90

by layer 11, and the projector output falls to 0.913. The decoder stays Q8_0,

where the output is correct.

q4_k was withdrawn. It loads and produces confident, well-formed text that

is not what is on the page — the worst failure mode for OCR. Its decoder is

anti-correlated with the reference by layer 2. Checkpoint-specific:

internvl2-1b and h2ovl-800m are fine at q4_k.

Attribution

Upstream © H2O.ai, Apache-2.0 — see

h2oai/h2ovl-mississippi-2b;

vision tower InternViT-300M is MIT. Conversion and quantization do not

relicense it. Per CrispEmbed POLICY.md, OCR output is a probabilistic

reconstruction, not a faithful copy.