Downloads · 30 days
35
24% of all-time downloads
LFM2.5-1.2B-Instruct-DSpark-5L-GGUF
tugot17/LFM2.5-1.2B-Instruct-DSpark-5L-GGUF
LFM2.5-1.2B-Instruct-DSpark-5L-GGUF is a machine learning model from tugot17. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for llama.cpp.
DSpark draft sidecar GGUF for mainline llama.cpp (DFlash/DSpark speculative decoding, merged in ggml-org/llama.cpp 25173). Converted from tugot17/LFM2.5-1.2B-Instruct-DSpark-5L with converthftogguf.py --target-model-d…
All-time downloads
147
Public
Repo size
594 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf594 MB · 100%
At a glance
- Library
- llama.cpp
- Access
- Public
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026
- SHA
- e7db315a
Base models
Model card
From the Hugging Face model README
LFM2.5-1.2B-Instruct DSpark 5L draft (GGUF)
DSpark draft sidecar GGUF for mainline llama.cpp (DFlash/DSpark speculative decoding, merged in ggml-org/llama.cpp #25173). Converted from tugot17/LFM2.5-1.2B-Instruct-DSpark-5L with convert_hf_to_gguf.py --target-model-dir <target>.
Pairs with the target model LiquidAI/LFM2.5-1.2B-Instruct-GGUF — the sidecar carries only the drafter (block size 7, rank-256 Markov head, confidence head); token embeddings and lm_head are shared from the target at load time.
Usage
llama-server -m <target>.gguf -md LFM2.5-1.2B-Instruct-DSpark-5L-draft-f16.gguf \
--spec-type draft-dspark --spec-draft-n-max 8 --spec-draft-n-min 0 \
-fa on -ngl 99
Greedy outputs are identical to the target alone; the timings field of each response reports draft_n / draft_n_accepted for acceptance-length tracking.
- Library
- llama.cpp
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026