https://github.com/mirage335
-
NVIDIA-Nemotron-Nano-9B-v2-virtuoso
372 Pulls 1 Tag Updated 1 month ago
-
Nemotron-3-Nano-30B-A3B-virtuoso
Possibly useful for agentic AI systems. Apparently compatible with ~16GB VRAM .
tools265 Pulls 1 Tag Updated 1 month ago
-
Llama-3-NeuralDaredevil-8B-abliterated-virtuoso
DANGER: CONVERSATION MAY DEVIATE FROM SAFE DESPITE HARMLESS PROMPTS. Embedded use only. NOT intended as-is for end-users
251 Pulls 1 Tag Updated 2 months ago
-
Llama-3_1-8B-Instruct-abliterated-virtuoso
DANGER: CONVERSATION MAY DEVIATE FROM SAFE DESPITE HARMLESS PROMPTS. Embedded use only. NOT intended as-is for end-users.
225 Pulls 1 Tag Updated 2 months ago
-
Qwen-3-VL-30B-A3B-Instruct-virtuoso
Recommended for transcribing and summarizing text from screenshots.
vision tools202 Pulls 1 Tag Updated 1 month ago
-
Qwen-3-VL-8B-Instruct-virtuoso
Recommended for transcribing and summarizing text from screenshots.
vision tools126 Pulls 1 Tag Updated 1 month ago
-
Qwen3-Coder-30b-virtuoso
From qwen3-coder:30b . Compatible with opencode (both).
tools100 Pulls 1 Tag Updated 2 months ago
-
Mistral-Small-3_2-24B-Instruct-2506-virtuoso
Generic all purpose model.
tools74 Pulls 1 Tag Updated 2 months ago
-
Llama-3_3-Valkyrie-49B-v1-INSTRUCT-virtuoso
Generates excellent search queries, title summaries, etc. Substantial track record. IQ2_XXS - Adequate for the strengths of this AI LLM model. Compatible with ~16GB VRAM. INSTRUCT version - should NOT generate thinking tokens.
tools63 Pulls 1 Tag Updated 2 months ago
-
Qwen-2_5-VL-7B-Instruct-virtuoso
Recommended for transcribing and summarizing text from screenshots.
vision59 Pulls 1 Tag Updated 2 months ago
-
Devstral-Small-2507-virtuoso
Generates good programming code, command line help, etc. Compatible with opencode .
tools57 Pulls 1 Tag Updated 2 months ago
-
Qwen-3-VL-32B-virtuoso
Recommended for transcribing and summarizing text from screenshots.
vision tools47 Pulls 1 Tag Updated 1 month ago
-
Llama-3_3-Nemotron-Super-49B-v1_5-virtuoso
Recommended for agentic AI systems. Apparently relatively decent long-horizon and complex problem solving ability. Significant track record. IQ2_XXS - Apparently adequate. Compatible with ~16GB VRAM.
43 Pulls 1 Tag Updated 2 months ago
-
gpt-oss-20b-virtuoso
Generic all purpose model. Occasionally may have notable logic, usually Llama-3_3-Nemotron-Super-49B-v1_5 is preferred.
tools thinking40 Pulls 1 Tag Updated 2 months ago
-
gpt-oss-120b-virtuoso
Generic all purpose model. Occasionally may have notable logic, usually Llama-3_3-Nemotron-Super-49B-v1_5 is preferred.
tools thinking36 Pulls 1 Tag Updated 2 months ago
-
Qwen-3-VL-30B-A3B-virtuoso
Recommended for transcribing and summarizing text from screenshots.
vision tools16 Pulls 1 Tag Updated 1 month ago
-
Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual-virtuoso
May be able to compare and explain the quality of other LLM responses.
15 Pulls 1 Tag Updated 2 months ago
-
Llama-3_3-Valkyrie-49B-v1-virtuoso
Generates excellent search queries, title summaries, etc. Substantial track record. IQ2_XXS - Adequate for the strengths of this AI LLM model. Compatible with ~16GB VRAM.
tools13 Pulls 1 Tag Updated 2 months ago
-
Magistral-Small-2506-virtuoso
Generic all purpose model.
tools thinking11 Pulls 1 Tag Updated 2 months ago