Filter by type:
Filter by tags:
huihui-qwen3.8-27b-abliterated
# Qwen3.8-27B
> [!Note]
> This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.
>
> These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.
> [!Tip]
> For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Qwen Cloud.
> In particular, **Qwen3.8-27B** will be available as a hosted version with more production features, e.g., 1M context length by default, official built-in tools. For more information, please refer to the Qwen3.8-27B Overview. The service is coming soon. Stay tuned for updates.
Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.
...
Repository: localaiLicense: apache-2.0
qwen3.8-27b-heretic-abliterated-uncensored
# Qwen3.8-27B
> [!Note]
> This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.
>
> These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.
> [!Tip]
> For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Qwen Cloud.
> In particular, **Qwen3.8-27B** will be available as a hosted version with more production features, e.g., 1M context length by default, official built-in tools. For more information, please refer to the Qwen3.8-27B Overview. The service is coming soon. Stay tuned for updates.
Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.
...
Repository: localaiLicense: apache-2.0
qwen3.8-27b-q4
Qwen3.8-27B is Qwen's dense 27B vision-language model for reasoning,
coding, tool use, and long-running agent tasks. It accepts text, images,
and video, and it supports a native context window of 262K tokens.
This default entry uses the official Q4_K_M GGUF and Q8_0 vision
projector. The linked variants add MTP speculative decoding or use the
higher-quality Q8_0 model.
Repository: localaiLicense: apache-2.0
qwen3.8-27b-q4-mtp
Qwen3.8-27B with the official Q4_K_M model and Q4_0 MTP draft model.
MTP speculative decoding can increase generation speed by proposing
multiple tokens for the target model to verify.
Repository: localaiLicense: apache-2.0
qwen3.8-27b-q8
Qwen3.8-27B in the official Q8_0 GGUF format. This variant provides higher
model fidelity for hosts with enough memory.
Repository: localaiLicense: apache-2.0
qwen3.8-27b-ridge
Qwen3.8-27B Ridge is a 3.69-bit mixed quantization that keeps the
Gated-DeltaNet state path at Q8_0 and preserves the embedded MTP head.
It reduces the model weights to 12.59 GB while retaining multimodal,
reasoning, coding, tool-use, and long-context capabilities.
Repository: localaiLicense: apache-2.0
grug-27b
Grug 27B is a multimodal Qwen3.5-derived model for chat, reasoning, vision,
and tool use. This entry uses the QAT Q4_K_M GGUF build.
Repository: localaiLicense: apache-2.0
grug-27b-q8
Grug 27B Q8 is the higher-precision Q8_0 GGUF build for multimodal chat,
reasoning, vision, and tool use.
Repository: localaiLicense: apache-2.0
grug-27b-mtp
Grug 27B MTP is the Q4_K_M GGUF build with multi-token prediction enabled
for speculative decoding, plus the shared vision projector.
Repository: localaiLicense: apache-2.0
qwythos-27b-v1
Qwythos-27B-v1 is an Apache-2.0 dense 27B reasoning and agentic model
derived from Qwen3.5-27B. It supports tool use, vision through the included
projector, and a one-million-token context window. This entry uses the
recommended Q4_K_M GGUF quantization; an MTP-enabled build is available as
a variant for hosts with recent llama.cpp support.
Repository: localaiLicense: apache-2.0
qwythos-27b-v1-mtp
Qwythos-27B-v1 MTP is the Q4_K_M build with its native multi-token
prediction head enabled for faster speculative decoding. It also includes
the shared vision projector and supports tool use and long-context
reasoning.
Repository: localaiLicense: apache-2.0
qwopus3.6-27b-fusion
Qwopus3.6-27B Fusion is an experimental Qwen3.6-27B merge that combines
reasoning and code-execution fine-tunes. It targets agentic coding,
mathematics, tool use, and long-context work while retaining image input.
This default entry uses the Q4_K_M GGUF quantization and the shared Q8_0
vision projector.
Repository: localaiLicense: qwen
qwopus3.6-27b-fusion-q8
Qwopus3.6-27B Fusion is an experimental Qwen3.6-27B reasoning and coding
merge. This entry uses the near-lossless Q8_0 GGUF quantization and the
shared Q8_0 vision projector.
Repository: localaiLicense: qwen
tess-4-27b
Tess-4-27B is an Apache-2.0 agentic and reasoning model built on
Qwen3.6-27B. It scales its thinking depth to the task and supports tool
use, long-context work, and image input. This default entry uses the
Q4_K_M GGUF quantization and the shared F16 vision projector.
Repository: localaiLicense: apache-2.0
tess-4-27b-q8
Tess-4-27B is an Apache-2.0 agentic and reasoning model built on
Qwen3.6-27B. This entry uses the near-lossless Q8_0 GGUF quantization and
the shared F16 vision projector.
Repository: localaiLicense: apache-2.0
tess-4-27b-mtp
Tess-4-27B with its Q4_K_M multi-token prediction draft enabled for
speculative decoding. The main model verifies every proposed token, and
the entry also includes the shared F16 vision projector.
Repository: localaiLicense: apache-2.0
qwen3.6-27b-fable-fusion-711-uncensored-heretic-nm-dau-neo-max-mtp
Important: This is the first fine tune to exceed 700 "arc-c" (The OpenAI, Claude and Gemini "zone of intelligence") in both 8 bit and 4 bit. This repo contains both "regular" and "MTP" Neo MAX Imatrix quants.
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF
The strongest, smartest open source multi-stage model fine tune for consumer hardware ever and BUILT on consumer hardware via Unsloth.
The first model of this size/type to breach "700" ARC-C in both 8 bit and 4 bit; hench the "711" in the name.
This model (both 4 bit and 8 bit) exceeds the base Qwen 3.6 27B in 6 out of 7 benchmarks, and matches it on the 7th AND exceeds all 7 benchmarks for Qwen3.6-35B-A3B.
The 700 "intelligence club" is reserved for OpenAI, Claude and Gemini closed source models.
This is the one they fear.
This is a multi-stage fine tune, multi-fine tune, and multi-stage merge.
A Colab between myself (multiple fine tunes, including multi-stage), Nightmedia (merge/benching), TeichAI (Polaris Dataset), armand0e (Light fable 5 traces) and trohrbaugh (heretic'ing the model).
...
Repository: localaiLicense: apache-2.0
bonsai-27b-1bit
Bonsai 27B (PrismML) is a full 27B-class reasoning model in end-to-end 1-bit weights,
derived from the Qwen3.6-27B hybrid-attention backbone (~75% linear attention, 262K
context). At a true 1.125 bits/weight it deploys in ~3.9 GB (~14.2x smaller than FP16)
while retaining 89.5% of FP16 intelligence across 15 thinking-mode benchmarks (math
91.66, coding 81.88). Ships an optional 4-bit vision tower (mmproj) for image input,
included here.
The Q1_0_g128 weights and hybrid-attention kernels are only in the PrismML llama.cpp
fork, so this runs on LocalAI's `bonsai` backend. A GPU is recommended. License: Apache 2.0.
Repository: localaiLicense: apache-2.0
ternary-bonsai-27b
Ternary Bonsai 27B (PrismML) is the quality-oriented operating point of the Bonsai 27B
family: full 27B-class reasoning in ternary {-1, 0, +1} weights on the Qwen3.6-27B
hybrid-attention backbone (262K context). At a true 1.71 bits/weight it deploys in
~7.2 GB (GGUF Q2_0_g128) and retains 95% of FP16 intelligence (80.49 average across 15
thinking-mode benchmarks) - a higher score than a conventional IQ2_XXS build at less
than two-thirds its footprint. Ships an optional 4-bit vision tower (mmproj), included.
The Q2_0 weights and hybrid-attention kernels are only in the PrismML llama.cpp fork,
so this runs on LocalAI's `bonsai` backend. A GPU is recommended. License: Apache 2.0.
Repository: localaiLicense: apache-2.0
ternary-bonsai-27b-pq2
Ternary Bonsai 27B (PrismML), GGUF PQ2_0 (packed Q2_0) ternary variant (~7.17 GB) with
the 4-bit vision tower (mmproj) included. Runs on LocalAI's `bonsai` backend.
License: Apache 2.0.
Repository: localaiLicense: apache-2.0
ternary-bonsai-27b-q2-g64
Ternary Bonsai 27B (PrismML), GGUF Q2_0 with group-64 packing (~7.59 GB), matching
llama.cpp's native 64-value Q2_0 block layout, with the 4-bit vision tower (mmproj)
included. Runs on LocalAI's `bonsai` backend. License: Apache 2.0.
Repository: localaiLicense: apache-2.0
Page 1