byczech

glm-4.7-flash-uncensored-16G-AU-IQ3_M

Uncensored GLM-4.7 Flash 30B text model with tool-calling support, quantized to IQ3_M and optimized for 16 GB VRAM. Suitable for coding, agents, automation, roleplay, analysis and unrestricted local experimentation.

tools thinking 30b

2,632 Pulls 1 Tag Updated 3 months ago

qwen3.6-mmproj-16G-UD-IQ3_S

Qwen 3.6 35B multimodal model with vision support, quantized to IQ3_S and optimized to fit within 16 GB VRAM with Q4_0 KV cache. Supports very large context windows, with the practical maximum depending on the Ollama version, GPU and backend.

vision tools thinking 35b

838 Pulls 1 Tag Updated 2 months ago

qwen3.6-16G-UD-IQ3_S

Qwen 3.6 35B text-only model, quantized to IQ3_S and optimized to fit within 16 GB VRAM with Q4_0 KV cache. Designed for long-context chat, coding, document analysis and general-purpose local inference. Supports very large context windows.

tools thinking 35b

595 Pulls 1 Tag Updated 3 months ago

glm-4.7-flash-16G-UD-Q3_K_XL

GLM-4.7 Flash 30B text model with tool-calling support, quantized to Q3_K_XL and optimized for 16 GB VRAM. The model supports up to 202,752 tokens context window, with approximately 136K fitting within 16 GB in suitable configurations.

tools thinking 30b

478 Pulls 1 Tag Updated 3 months ago

gemma4-it-mmproj-16G-Q3_K_S

Gemma 4 31B multimodal instruct model with vision support, quantized to Q3_K_S and optimized for 16 GB VRAM. Supports a practical context window of approximately 36K–40K tokens, depending on the Ollama version, GPU, backend and runtime configuration.

vision tools thinking 31b

412 Pulls 1 Tag Updated 2 months ago

glm-4.7-flash-12G-UD-IQ2_XSS

GLM-4.7 Flash 30B text model with tool-calling support, quantized to IQ2_XSS and optimized for 12 GB VRAM. Supports a maximum context window of 202,752 tokens, subject to the Ollama version, GPU, backend and runtime configuration.

tools thinking 30b

370 Pulls 1 Tag Updated 3 months ago

glm-4.7-flash-16G-UD-IQ3_XSS

GLM-4.7 Flash 30B text model with tool-calling support, quantized to IQ3_XSS and optimized for 16 GB VRAM. The model supports up to 202,752 tokens context window, with approximately 180K fitting within 16 GB in suitable configurations.

tools thinking 30b

239 Pulls 1 Tag Updated 3 months ago

gemma4-it-16G-Q3_K_S

Gemma 4 31B text-only instruct model with tool-calling and thinking support, quantized to Q3_K_S and optimized for 16 GB VRAM. Supports up to 256K context, with approximately 64K tokens fitting fully within 16 GB VRAM in tested configurations.

tools thinking 31b

184 Pulls 1 Tag Updated 3 months ago