Filter by type:
Filter by tags:
](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
qwopus3.8-27b-flash-v2
Qwopus3.8-27B-Flash-V2 is a new post-training release for reasoning and agent
workloads. This Q4_K_M GGUF includes the F32 vision projector and uses
llama.cpp's embedded chat template with MTP speculative decoding.
Repository: localaiLicense: apache-2.0
qwopus3.8-27b-flash-v2-q8
Qwopus3.8-27B-Flash-V2 is a new post-training release for reasoning and agent
workloads. This Q8_0 GGUF includes the F32 vision projector and uses
llama.cpp's embedded chat template with MTP speculative decoding.
Repository: localaiLicense: apache-2.0
qwopus3.8-27b-flash
Qwopus3.8-27B-Flash is a Qwen3.8-27B fine-tune for reasoning and agent
workloads. This Q4_K_M GGUF includes the F32 vision projector and uses
llama.cpp's embedded chat template with MTP speculative decoding.
The publisher reports a known Python code indentation issue.
Repository: localaiLicense: apache-2.0
qwopus3.8-27b-flash-q8
Qwopus3.8-27B-Flash is a Qwen3.8-27B fine-tune for reasoning and agent
workloads. This Q8_0 GGUF includes the F32 vision projector and uses
llama.cpp's embedded chat template with MTP speculative decoding.
The publisher reports a known Python code indentation issue.
Repository: localaiLicense: apache-2.0
mimo-v2.6-distill-qwen-9b
MiMo-V2.6-Distill-Qwen-9B is Xiaomi MiMo's 9B Qwen3.5 fine-tune for coding, agent tasks, and visual coding.
This Q4_K_M GGUF build uses llama.cpp with the model's embedded chat template and includes the F16 vision projector.
Repository: localaiLicense: mit
mimo-v2.6-distill-qwen-9b-q8
MiMo-V2.6-Distill-Qwen-9B is Xiaomi MiMo's 9B Qwen3.5 fine-tune for coding, agent tasks, and visual coding.
This Q8_0 GGUF build uses llama.cpp with the model's embedded chat template and includes the F16 vision projector.
Repository: localaiLicense: mit
thinkingcap-qwen3.8-27b
ThinkingCap is a 27B Qwen3.8 fine-tune trained to reduce reasoning tokens, with text and image input.
This Q4_K_M GGUF build uses llama.cpp, the embedded chat template, and the F16 vision projector.
Licensed under PolyForm Small Business 1.0.0 with the publisher's personal-use grant; see the model license for permitted use.
Repository: localaiLicense: polyform-small-business-1.0.0
thinkingcap-qwen3.8-27b-q8
ThinkingCap is a 27B Qwen3.8 fine-tune trained to reduce reasoning tokens, with text and image input.
This Q8_0 GGUF build uses llama.cpp, the embedded chat template, and the F16 vision projector.
Licensed under PolyForm Small Business 1.0.0 with the publisher's personal-use grant; see the model license for permitted use.
Repository: localaiLicense: polyform-small-business-1.0.0
hemmingway-1
Hemmingway-1 is Altworld's English-first 27B text model, fine-tuned from Qwen3.8-27B for everyday messages and creative writing.
This Q4_K_M GGUF build uses llama.cpp and the model's embedded chat template. Licensed under CC BY-NC 4.0; commercial use requires a separate agreement.
Repository: localaiLicense: cc-by-nc-4.0
hemmingway-1-q8
Hemmingway-1 is Altworld's English-first 27B text model, fine-tuned from Qwen3.8-27B for everyday messages and creative writing.
This Q8_0 GGUF build uses llama.cpp and the model's embedded chat template. Licensed under CC BY-NC 4.0; commercial use requires a separate agreement.
Repository: localaiLicense: cc-by-nc-4.0
supra2-100m-instruct
Supra2-100M-Instruct is a compact English chat model trained from scratch by
SupraLabs on the Qwen3 architecture. It has 100 million parameters, a
2,048-token context window, and is intended for lightweight experiments and
constrained edge deployments. This entry uses the publisher's official F16
GGUF build.
Repository: localaiLicense: apache-2.0
huihui-qwen3.8-flash-next-abliterated-q4
Huihui's abliterated Qwen3.8-Flash-Next is a vision-language
mixture-of-experts model modified to reduce refusals. This entry uses
the publisher's UD-Q4_K_XL GGUF and BF16 vision projector for text chat
and image input through llama.cpp. The default context is 32,768 tokens.
Model weights use the Qwen Community License 1.0.
Repository: localaiLicense: other
qwen3.8-flash-next-gsq-rco-q2-0
Qwen3.8 Flash Next with ISTA DASLab's GSQ-RCO Q2_0 mixed quantization.
Includes both GGUF shards (transformer weights and n-gram embeddings)
and the BF16 vision projector for text chat and image input.
Uses llama.cpp with the embedded chat template and a 32K context.
Repository: localaiLicense: other
qwen3.8-flash-next-gsq-rco-iq2-xs
Qwen3.8 Flash Next with ISTA DASLab's GSQ-RCO IQ2_XS mixed quantization.
Includes both GGUF shards (transformer weights and n-gram embeddings)
and the BF16 vision projector for text chat and image input.
Uses llama.cpp with the embedded chat template and a 32K context.
Repository: localaiLicense: other
qwen3.8-flash-next-gsq-rco-iq3-xxs
Qwen3.8 Flash Next with ISTA DASLab's GSQ-RCO IQ3_XXS mixed quantization.
Includes both GGUF shards (transformer weights and n-gram embeddings)
and the BF16 vision projector for text chat and image input.
Uses llama.cpp with the embedded chat template and a 32K context.
Repository: localaiLicense: other
dfm-mimir:vllm
DFM Mimir is an Apache-2.0, instruction-tuned HRM-Text model from Danish
Foundation Models. It has about 1 billion parameters and a 4,096-token
context window. The model focuses on Danish and English chat, reasoning,
mathematics, and code generation, and uses only permissible post-training
data. This entry serves the official BF16 safetensors checkpoint with vLLM.
Repository: localaiLicense: apache-2.0
granite-4.2-3b-q4
IBM Granite 4.2 3B is a compact multilingual reasoning model for chat,
coding, long-context tasks, and tool use. This entry uses the Q4_K_M
GGUF; a higher-fidelity Q8_0 build is available as a variant.
Repository: localaiLicense: apache-2.0
granite-4.2-3b-q8
IBM Granite 4.2 3B in the higher-fidelity Q8_0 GGUF format. It is a
compact multilingual reasoning model for chat, coding, and tool use.
Repository: localaiLicense: apache-2.0
granite-4.2-8b-q4
IBM Granite 4.2 8B is a multilingual reasoning model for chat, coding,
long-context tasks, and tool use. This entry uses the Q4_K_M GGUF; a
higher-fidelity Q8_0 build is available as a variant.
Repository: localaiLicense: apache-2.0
granite-4.2-8b-q8
IBM Granite 4.2 8B in the higher-fidelity Q8_0 GGUF format. It is a
multilingual reasoning model for chat, coding, and tool use.
Repository: localaiLicense: apache-2.0
Page 1