Model Gallery
Discover and install AI models from our curated collection
Find Your Perfect Model
Filter by Model Type
Browse by Tags
swift-1.5-qwen3.8-flash-next-iq2_xs
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
UkisAI's Swift 1.5 fine-tune, which thinks much shorter before it answers, at
2-bit i-quant (IQ2_XS) (about 69 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 39 GB of RAM and VRAM together for the model (the same as the same
size of the original), and fast SSD storage for the n-gram table. Needs a GPU
the strata backend supports; NVIDIA with 12 GB of VRAM or more is the class
Strata tests. Runs only on the experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Two licences apply: UkisAI's Swift Open License 1.0 for the fine-tune, and the
Qwen Community License 1.0 for the Qwen3.8-Flash-Next parts it is built from.
Read both before you offer the model to other people.
The GGUF files are the quantization by UkisAI of its Swift 1.5 fine-tune;
Strata is by Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: swift-open-license-1.0
swift-1.5-qwen3.8-flash-next-iq3_xxs
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
UkisAI's Swift 1.5 fine-tune, which thinks much shorter before it answers, at
3-bit i-quant (IQ3_XXS) (about 77 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 47 GB of RAM and VRAM together for the model (the same as the same
size of the original), and fast SSD storage for the n-gram table. Needs a GPU
the strata backend supports; NVIDIA with 12 GB of VRAM or more is the class
Strata tests. Runs only on the experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Two licences apply: UkisAI's Swift Open License 1.0 for the fine-tune, and the
Qwen Community License 1.0 for the Qwen3.8-Flash-Next parts it is built from.
Read both before you offer the model to other people.
The GGUF files are the quantization by UkisAI of its Swift 1.5 fine-tune;
Strata is by Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: swift-open-license-1.0
swift-1.5-qwen3.8-flash-next-iq3_s
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
UkisAI's Swift 1.5 fine-tune, which thinks much shorter before it answers, at
3.5-bit i-quant (IQ3_S) (about 85 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 55 GB of RAM and VRAM together for the model (the same as the same
size of the original), and fast SSD storage for the n-gram table. Needs a GPU
the strata backend supports; NVIDIA with 12 GB of VRAM or more is the class
Strata tests. Runs only on the experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Two licences apply: UkisAI's Swift Open License 1.0 for the fine-tune, and the
Qwen Community License 1.0 for the Qwen3.8-Flash-Next parts it is built from.
Read both before you offer the model to other people.
The GGUF files are the quantization by UkisAI of its Swift 1.5 fine-tune;
Strata is by Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: swift-open-license-1.0
gemma-4-e2b-it-artemis-q3-k-l
TurinTech Artemis Q3_K_L quantization of Gemma 4 E2B from Google's QAT
checkpoint, for local chat and tool calls. Accepts image input through
the bundled F16 vision projector. Uses the embedded chat template and
an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e2b-it-artemis-q3-k-m
TurinTech Artemis Q3_K_M quantization of Gemma 4 E2B from Google's QAT
checkpoint, for local chat and tool calls. Accepts image input through
the bundled F16 vision projector. Uses the embedded chat template and
an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e2b-it-artemis-iq3-xxs
TurinTech Artemis IQ3_XXS quantization of Gemma 4 E2B from Google's QAT
checkpoint, for local chat and tool calls. Accepts image input through
the bundled F16 vision projector. Uses the embedded chat template and
an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e2b-it-artemis-iq2-m
TurinTech Artemis IQ2_M quantization of Gemma 4 E2B from Google's QAT
checkpoint, for local chat and tool calls. Accepts image input through
the bundled F16 vision projector. Uses the embedded chat template and
an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e4b-it-artemis-q4-0
TurinTech Artemis Q4_0 quantization of Gemma 4 E4B from Google's QAT
checkpoint, for local chat, reasoning, and tool use. Accepts image
input through the bundled F16 vision projector. Uses the embedded chat
template and an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e4b-it-artemis-iq3-m
TurinTech Artemis IQ3_M quantization of Gemma 4 E4B from Google's QAT
checkpoint, for local chat, reasoning, and tool use. Accepts image
input through the bundled F16 vision projector. Uses the embedded chat
template and an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e4b-it-artemis-q3-k-m
TurinTech Artemis Q3_K_M quantization of Gemma 4 E4B from Google's QAT
checkpoint, for local chat, reasoning, and tool use. Accepts image
input through the bundled F16 vision projector. Uses the embedded chat
template and an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
qwen3.5-0.8b-artemis-q5
TurinTech Artemis Q5_K_M quantization of Qwen3.5 0.8B for text chat,
reasoning, and tool use. This text-only build omits the vision encoder
and MTP layer. Uses the embedded chat template and an 8192-token context.
Repository: localaiLicense: apache-2.0
qwen3.5-0.8b-artemis-q4
TurinTech Artemis Q4_K_M quantization of Qwen3.5 0.8B for text chat,
reasoning, and tool use. This text-only build omits the vision encoder
and MTP layer. Uses the embedded chat template and an 8192-token context.
Repository: localaiLicense: apache-2.0
qwen3.5-2b-artemis-q5-k-m
TurinTech Artemis Q5_K_M quantization of Qwen3.5 2B for local tool calls,
maths, and instruction following. Accepts image input through the
bundled F16 vision projector. Uses the embedded chat template and an
8192-token context.
Repository: localaiLicense: apache-2.0
qwen3.5-2b-artemis-q4-k-m
TurinTech Artemis Q4_K_M quantization of Qwen3.5 2B for local tool calls,
maths, and instruction following. Accepts image input through the
bundled F16 vision projector. Uses the embedded chat template and an
8192-token context.
Repository: localaiLicense: apache-2.0
qwen3.5-4b-artemis-q4-k-m
TurinTech Artemis Q4_K_M quantization of Qwen3.5 4B for local chat and
tool calls. Accepts image input through the bundled F16 vision
projector. Uses the embedded chat template and an 8192-token context.
Repository: localaiLicense: apache-2.0
qwen3.5-4b-artemis-q5-k-m
TurinTech Artemis Q5_K_M quantization of Qwen3.5 4B for local chat and
tool calls. Accepts image input through the bundled F16 vision
projector. Uses the embedded chat template and an 8192-token context.
Repository: localaiLicense: apache-2.0
qwen3.5-4b-artemis-q5-k-s
TurinTech Artemis Q5_K_S quantization of Qwen3.5 4B for local chat and
tool calls. Accepts image input through the bundled F16 vision
projector. Uses the embedded chat template and an 8192-token context.
Repository: localaiLicense: apache-2.0
qwen3.5-9b-artemis-q4-k-m
TurinTech Artemis Q4_K_M quantization of Qwen3.5 9B for local chat and
tool calls. Accepts image input through the bundled F16 vision
projector. Uses the embedded chat template and an 8192-token context.
Repository: localaiLicense: apache-2.0
qwen3.5-9b-artemis-q5-k-s
TurinTech Artemis Q5_K_S quantization of Qwen3.5 9B for local chat and
tool calls. Accepts image input through the bundled F16 vision
projector. Uses the embedded chat template and an 8192-token context.
Repository: localaiLicense: apache-2.0
qwen3.5-9b-artemis-iq4-xs
TurinTech Artemis IQ4_XS quantization of Qwen3.5 9B for local chat and
tool calls. Accepts image input through the bundled F16 vision
projector. Uses the embedded chat template and an 8192-token context.
Repository: localaiLicense: apache-2.0
ornith-1.5-9b-uncensored
# Ornith-1.5-9B-uncensored
An **abliterated** (refusal-direction-ablated) build of
`ornith-ai/Ornith-1.5-9B`, produced with
ZeroFuse and published by
junafinity.
This is the **9B control checkpoint** (bf16). Mac users should start from the MLX-8bit or GGUF-8bit siblings. The official 9B base has **no `mtp.*` tensors**; nothing was grafted.
**Vision tower and MTP heads are preserved** — see
Vision & MTP preservation for the before/after audit.
## Intended use: red teaming and defensive cybersecurity research
These uncensored (abliterated) weights are built as a **research instrument** for red teaming and defensive cybersecurity work. Safety training suppresses the *display* of capability, not capability itself. A refusal tells you the model declined. It does not tell you whether the weights could have complied. That conflation underestimates the true ceiling and hides holes in *your* filters, classifiers, and policy layer.
Use each uncensored checkpoint as the **treatment half of a controlled pair** against its original base model:
...
Repository: localaiLicense: apache-2.0
Page
1
of many