Lucebox/Laguna-XS-2.1-DFlash-GGUF

Model

4

stars

4

commits

2

linked in READMEs

Jul 9, 2026

updated

dflash

endpoints_compatible

gguf

laguna

lucebox

speculative-decoding

README

Laguna-XS-2.1-DFlash-GGUF (quantized drafter)

Quantized GGUF builds of the official poolside/Laguna-XS-2.1-DFlash speculator, packaged for the Lucebox inference engine's speculative decoding of poolside/Laguna-XS-2.1.

file	scheme	size	notes
`laguna-xs21-dflash-q4.gguf`	Q4_0 projections, Q8_0 feature projection (fc), F32 norms	271 MB	recommended
`laguna-xs21-dflash-q8.gguf`	Q8_0 projections, F32 norms	492 MB	conservative

Because speculative decoding verifies every draft against the target model, drafter quantization cannot change the target's greedy output quality; the only quantity at stake is acceptance length. Measured on an RTX 3090 with the Laguna XS 2.1 Q4_K_M target (HumanEval/GSM8K/Math screens): acceptance unchanged vs the BF16 drafter, end-to-end decode ~+3% (q4), gold-scored task accuracy identical.

Produced with server/scripts/requant_dflash_draft.py from the lucebox engine tree (GGUF-to-GGUF requant; all metadata, gates and aux norms preserved).

License: OpenMDW-1.1, inherited from the base speculator. All credit for the DFlash speculator weights to poolside.

Contributors

4 commits

Similar repos

Lucebox/gemma-4-26B-A4B-it-DFlash-GGUF

2

Lucebox/gemma-4-31B-it-DFlash-GGUF

7

bleysg/DeepSeek-V4-Flash-DSpark-drafter-GGUF

6

incoai/Qwen3.8-27B-DFlash2-GGUF

155

bloomer010/Ling-3.0-flash-GGUF

27

kingjones777/Laguna-S-2.1-ROCmFP4-STRIX_LEAN-GGUF

2

JonathanColetti/Qwen3.8-27B-Uncensored-GGUF

1,004

cafonez/Escha-W2-35B-A3B-ROCmFP2

14

Linked in READMEs

Luce-Org/lucebox

LLM speculative inference server for heterogeneous hardware & consumer GPUs

2,843

Luce-Org/lucebox-hub

LLM speculative inference server for heterogeneous hardware & consumer GPUs

2,843

Lucebox/Laguna-XS-2.1-DFlash-GGUF

Model

4

stars

4

commits

2

linked in READMEs

Jul 9, 2026

updated

dflash

endpoints_compatible

gguf

laguna

lucebox

speculative-decoding

README

Laguna-XS-2.1-DFlash-GGUF (quantized drafter)

Quantized GGUF builds of the official poolside/Laguna-XS-2.1-DFlash speculator, packaged for the Lucebox inference engine's speculative decoding of poolside/Laguna-XS-2.1.

file	scheme	size	notes
`laguna-xs21-dflash-q4.gguf`	Q4_0 projections, Q8_0 feature projection (fc), F32 norms	271 MB	recommended
`laguna-xs21-dflash-q8.gguf`	Q8_0 projections, F32 norms	492 MB	conservative

Because speculative decoding verifies every draft against the target model, drafter quantization cannot change the target's greedy output quality; the only quantity at stake is acceptance length. Measured on an RTX 3090 with the Laguna XS 2.1 Q4_K_M target (HumanEval/GSM8K/Math screens): acceptance unchanged vs the BF16 drafter, end-to-end decode ~+3% (q4), gold-scored task accuracy identical.

Produced with server/scripts/requant_dflash_draft.py from the lucebox engine tree (GGUF-to-GGUF requant; all metadata, gates and aux norms preserved).

License: OpenMDW-1.1, inherited from the base speculator. All credit for the DFlash speculator weights to poolside.

Similar repos

Lucebox/gemma-4-26B-A4B-it-DFlash-GGUF

2

Lucebox/gemma-4-31B-it-DFlash-GGUF

7

bleysg/DeepSeek-V4-Flash-DSpark-drafter-GGUF

6

incoai/Qwen3.8-27B-DFlash2-GGUF

155

bloomer010/Ling-3.0-flash-GGUF

27

kingjones777/Laguna-S-2.1-ROCmFP4-STRIX_LEAN-GGUF

2

JonathanColetti/Qwen3.8-27B-Uncensored-GGUF

1,004

cafonez/Escha-W2-35B-A3B-ROCmFP2

14

Linked in READMEs

Luce-Org/lucebox

LLM speculative inference server for heterogeneous hardware & consumer GPUs

2,843

Luce-Org/lucebox-hub

LLM speculative inference server for heterogeneous hardware & consumer GPUs

2,843

Contributors

4 commits