Modelpublic

PollardWeights/Spark-X2.5-4B-Pollard

sourceHugging Faceapache-2.0updated 15d agoView on Hugging Face

1likes963downloads

Model Card

Spark-X2.5-4B — Pollard

### Pollard shrank this model: 8.22 GB (f16) → 1.93 GB — 77% smaller, 4.3× down. The smallest rung here; larger, higher-fidelity rungs are listed below. | format | this model's size | |---|---:| | f16 | 8.22 GB | | Q80 | ~4.36 GB | | Q6K | ~3.37 GB | | Q4KM | ~2.38 GB | | PollardMix (this repo's IQ3_S) | 1.93 GB |

Pollard builds of XHToken/Spark-X2.5-4B made with Pollard Weights — a ladder of measured-allocation quants (bits placed by per-layer sensitivity, not a uniform crush).

Standard GGUF, but you need a recent llama.cpp. This model's architecture (spark2_5) is implemented upstream, so any build new enough to carry it runs these files -- llama.cpp itself, and Ollama or LM Studio once they ship a runtime with it. An older build will refuse them with unknown model architecture. The quants are ordinary K-quants.

Model details


Parameter count	~4.1B
Architecture	`spark2_5`
Input support	text
imatrix	no
Perplexity measured	yes — table below

Which file should I choose?

Every rung is the same weights, sized to a different RAM budget by the measured allocation. Pick the largest one that fits your machine with room for context:

—~5 GB RAM / VRAM → `Q6_K` (3.38 GB). (needs a current llama.cpp) near-lossless
—~4 GB RAM / VRAM → `IQ4_XS` (2.42 GB). (needs a current llama.cpp) recommended default
—~4 GB RAM / VRAM → `IQ3_S` (1.93 GB). (needs a current llama.cpp) smallest

Available files (Calib 3.0 corpus, ctx 512, 6 chunks)

f16 reference PPL 6.091...

file	PPL	size	Mean KLD	notes
`Spark-X2.5-4B-Pollard-IQ3_S.gguf`	6.781	1.93 GB	—	smallest
`Spark-X2.5-4B-Pollard-IQ4_XS.gguf`	6.207	2.42 GB	—	recommended default
`Spark-X2.5-4B-Pollard-Q6_K.gguf`	6.099	3.38 GB	—	near-lossless

Measured notes

f16 reference PPL 6.091.

Measured notes

f16 reference PPL 6.091..

Download a specific file

bash

pip install -U "huggingface_hub[cli]"
hf download PollardWeights/Spark-X2.5-4B-Pollard \
  --include "Spark-X2.5-4B-Pollard-IQ4_XS.gguf" --local-dir ./

How to run

This model's architecture (spark2_5) needs a llama.cpp new enough to carry it, so build or update from upstream first:

bash

llama-cli    -m Spark-X2.5-4B-Pollard-IQ4_XS.gguf -ngl 99 -p "Explain why the sky is blue."
llama-server -m Spark-X2.5-4B-Pollard-IQ4_XS.gguf -ngl 99

Ollama and LM Studio will run these once their bundled llama.cpp carries spark2_5.

ARM / AVX

llama.cpp repacks weights into an interleaved layout at load time for faster inference on ARM and AVX machines — no special file needed, online repacking covers these quants. The old Q4_0_4_4/4_8/8_8 variants are not required.

Errata

—general.architecture is spark2_5, which upstream llama.cpp added recently. A build older than that support refuses these files with unknown model architecture — update llama.cpp rather than looking for a different quant. Checked with pollard-ggufcheck, which reads the architecture and the tensor types out of the header and asks upstream what it implements.
—Measured allocation places bits by per-layer sensitivity under a size budget.
—Single machine; replication invited.

Credits & license

—Base model: `XHToken/Spark-X2.5-4B`
—Quantization tooling: llama.cpp (ggml-org)
—Method + tooling: Pollard Weights — measure first, no claim before a number.
—License: apache-2.0, inherited from the base model.

Built with [Pollard Weights](https://github.com/WestWaters/pollard-weights) — frontier models, small hardware, no compromise.