Downloads · 30 days
8
47% of all-time downloads
posit-ds
dpletta/posit-ds
posit-ds is a text generation model from dpletta. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Ollama packaging of Unsloth Dynamic UD-Q4KM of Qwen3.8-27B for Posit Assistant on a 24 GB Apple Silicon Mac. Thinking is on; default effort is medium (Qwen's own default is xhigh, which is too verbose for an editor ag…
All-time downloads
17
Public
Repo size
13.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf13.8 GB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026
- SHA
- bdc8a112
Try a prompt
Base models
Model card
From the Hugging Face model README
posit-ds
Ollama packaging of Unsloth Dynamic UD-Q4_K_M of
Qwen3.8-27B for Posit Assistant on a
24 GB Apple Silicon Mac. Thinking is on; default effort is medium (Qwen's
own default is xhigh, which is too verbose for an editor agent).
This is not a new training run. Weights come from
unsloth/Qwen3.8-27B-GGUF
(Qwen3.8-27B-UD-Q4_K_M.gguf, ~16.5 GB). License: Apache-2.0. Vision mmproj
is omitted on purpose so the KV cache still fits.
num_ctx is capped at 16384. 32K plus medium thinking starves a 24 GB Mac.
Run
ollama run hf.co/dpletta/posit-ds
# or, after `ollama create` / `ollama pull`:
ollama run dpletta/posit-ds
Native API: "think": "medium". OpenAI-compatible: "reasoning_effort": "medium".
Do not override TEMPLATE.
- Task
- Text Generation
- License
- apache-2.0
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026