Filter by type:
Filter by tags:
lfm2.5-24b-a2b-turbo-brilliance-iq4-xs
DavidAU's Turbo Brilliance build of LFM2.5-24B-A2B, a text-only reasoning
model with 24B total parameters and 2.45B active parameters. This entry
uses the IQ4_XS GGUF quantization and the embedded Turbo Brilliance
chat template for multilingual chat and tool use.
Repository: localaiLicense: other
lfm2.5-24b-a2b-turbo-brilliance-q8
DavidAU's Turbo Brilliance build of LFM2.5-24B-A2B, a text-only reasoning
model with 24B total parameters and 2.45B active parameters. This entry
uses the Q8_0 MAX GGUF quantization and the embedded Turbo Brilliance
chat template for multilingual chat and tool use.
Repository: localaiLicense: other
spark-x2.6-4b-q4
Spark-X2.6-4B is XHToken's 4B text model for conversation, reasoning,
coding, and multilingual tasks. This build uses Q4_K_M GGUF weights,
the embedded Jinja chat template, and a 32K-token default context.
Repository: localaiLicense: apache-2.0
spark-x2.6-4b-q8
Spark-X2.6-4B is XHToken's 4B text model for conversation, reasoning,
coding, and multilingual tasks. This build uses Q8_0 GGUF weights,
the embedded Jinja chat template, and a 32K-token default context.
Repository: localaiLicense: apache-2.0
lfm2.5-24b-a2b-ud-q4
LiquidAI LFM2.5-24B-A2B is a text-only reasoning model with 24B total
parameters and 2.45B active parameters for multilingual chat and tool use.
This entry uses Unsloth's dynamic UD-Q4_K_XL GGUF quantization.
Repository: localaiLicense: other
lfm2.5-24b-a2b-ud-q6
LiquidAI LFM2.5-24B-A2B is a text-only reasoning model with 24B total
parameters and 2.45B active parameters for multilingual chat and tool use.
This entry uses Unsloth's dynamic UD-Q6_K_XL GGUF quantization.
Repository: localaiLicense: other
atomic-lfm2.5-24b-a2b-uncensored
AtomicChat's LFM2.5-24B-A2B derivative reduces refusal behavior in the
original weights. This text-only mixture-of-experts model has 24B total
parameters and supports multilingual reasoning and tool use.
This entry uses the AD-Q4_K_M GGUF build with the edits baked in.
Repository: localaiLicense: other
atomic-lfm2.5-24b-a2b-uncensored-q6
AtomicChat's LFM2.5-24B-A2B derivative reduces refusal behavior in the
original weights. This text-only mixture-of-experts model has 24B total
parameters and supports multilingual reasoning and tool use.
This entry uses the AD-Q6_K GGUF build with the edits baked in.
Repository: localaiLicense: other
atomic-lfm2.5-24b-a2b-uncensored-q8
AtomicChat's LFM2.5-24B-A2B derivative reduces refusal behavior in the
original weights. This text-only mixture-of-experts model has 24B total
parameters and supports multilingual reasoning and tool use.
This entry uses the AD-Q8_0 GGUF build with the edits baked in.
Repository: localaiLicense: other
spark-s1-4b-v6
spark-s1-4b-v6 is a Qwen3.5-4B decision model (Open Spark Jev): given a state and a question with a fixed menu of options it
returns a calibrated probability per option from the first-token logprobs of the option letters. It is not a chat model:
send the rendered prompt to /v1/completions with max_tokens 1, logprobs true, and top_logprobs 20.
Check that every option letter appears in the returned probabilities. Then apply softmax(logprob / 1.481) over those letters.
Q8_0 GGUF (agrees with the bf16 model on 99.5% of held-out decisions).
Repository: localaiLicense: apache-2.0
](images/xhtoken-wechat.jpg){kind=icon}
spark-x2.5-4b
# Spark-X2.5
[](https://join.slack.com/t/tokenspark/shared_invite/zt-432qf8l2f-5~dLyXv8uETr0P0UuC07nw)
[](https://discord.gg/kTDE2Hg8aw)
[](https://www.youtube.com/@SparkLLM)
[](https://dev.to/sparkllm)
[](https://bsky.app/profile/sparkllm.bsky.social)
[](https://x.com/sparkllm)
[](https://www.zhihu.com/people/zhiikz7qh7m)
[](images/xhtoken-wechat.jpg)
> [!Note]
> This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.
## Introduction
We are introducing Spark-X2.5-4B and Spark-X2.5-1.7B, two compact, general-purpose language models designed to make capable AI more practical, efficient, and accessible. The models deliver strong performance across a broad range of everyday tasks—including conversation, writing, translation, reasoning, coding, tool use, and agentic workflows—achieving leading results among open-source models of comparable size. Spark-X2.5 combines an efficiency-oriented architecture with native context windows of up to 1M tokens, and support for more than 200 languages.
...
Repository: localaiLicense: apache-2.0
qwen3.8-flash-next-atomic-iq4
Qwen3.8 Flash Next in AtomicChat's AD-3.84bpw IQ4_XS M64 GGUF
build, with the F16 vision projector. The n-gram table occupies a
separate shard. This entry enables memory mapping and disables llama.cpp
automatic parameter fitting as required by the publisher.
Repository: localaiLicense: other
Attention: Trust Remote Code is required for this model
wemm-embedding-4b
WeMM-Embedding-4B is Tencent's mid-sized Apache-2.0 multilingual embedding
model built on Qwen3.5. This entry serves the original bfloat16 safetensors
with LocalAI's Transformers backend and produces 2,560-dimensional
normalized embeddings for text retrieval, semantic search, and RAG.
The upstream model can also embed images and videos. LocalAI currently
exposes text input through its embeddings API for this backend.
Repository: localaiLicense: apache-2.0
byteshape-qwen3.8-27b
ByteShape's ShapeLearn quantization of Qwen3.8 27B for chat, reasoning,
coding, and image input. This IQ4_XS-3.84bpw build uses mixed tensor
precisions and includes a BF16 vision projector. MTP decoding is enabled.
Repository: localaiLicense: apache-2.0
spark-x2.5-4b-heretic-jp-q4
Spark-X2.5-4B Heretic JP is a Japanese adaptation of Spark-X2.5-4B with
continued pretraining, instruction tuning, and tool-call training.
This Q4_K_M GGUF uses the embedded chat template and an 8K-token default
context. Allow at least 1024 output tokens for thinking and the answer.
Repository: localaiLicense: apache-2.0
spark-x2.5-4b-heretic-jp-q8
Spark-X2.5-4B Heretic JP is a Japanese adaptation of Spark-X2.5-4B with
continued pretraining, instruction tuning, and tool-call training.
This Q8_0 GGUF uses the embedded chat template and an 8K-token default
context. Allow at least 1024 output tokens for thinking and the answer.
Repository: localaiLicense: apache-2.0
sharp-spark-x2.5-4b
Sharp-Spark is an imatrix quantization of XHToken's Spark-X2.5-4B text model
with an adjusted chat template for coding. This Q4_K_XL build uses the
embedded Sharp-Spark template and a 32K-token default context.
Repository: localaiLicense: apache-2.0
sharp-spark-x2.5-4b-q5
Sharp-Spark is an imatrix quantization of XHToken's Spark-X2.5-4B text model
with an adjusted chat template for coding. This Q5_K_XL build uses the
embedded Sharp-Spark template and a 32K-token default context.
Repository: localaiLicense: apache-2.0
sharp-spark-x2.5-4b-q6
Sharp-Spark is an imatrix quantization of XHToken's Spark-X2.5-4B text model
with an adjusted chat template for coding. This Q6_K_XL build uses the
embedded Sharp-Spark template and a 32K-token default context.
Repository: localaiLicense: apache-2.0
spark-x2.5-4b-q4
Spark-X2.5-4B is XHToken's 4B text model for conversation, reasoning,
coding, and multilingual tasks. This entry uses Q4_K_M GGUF weights;
Q6_K and Q8_0 builds are available as variants. All builds use the
embedded Jinja chat template and a 32K-token default context.
Repository: localaiLicense: apache-2.0
spark-x2.5-4b-q6
Spark-X2.5-4B in Q6_K GGUF format, with the embedded Jinja chat
template and a 32K-token default context.
Repository: localaiLicense: apache-2.0
Page 1