Recommended starter~5.63 GB
Q4_K_M
Compact and practical first choice. Start here unless you already know your machine has enough RAM or VRAM for larger variants.
PB_qwen3_5_9b_dora-Q4_K_M.gguf
PowerBASIC model library
Additional AI Model Downloads
PowerBASIC-focused Qwen 9B DoRA GGUF model variants for local AI runtimes such as LM Studio, Ollama, llama.cpp-compatible tools, KoboldCpp, text-generation-webui, and other GGUF-capable local inference environments.
These downloads are optional companions for users who want local model behavior tuned toward PowerBASIC-oriented code assistance. Choose the quantization level that matches your available RAM/VRAM.
The GGUF files are hosted in the shared download area outside AISPR and can be used in LM Studio, Ollama imports, llama.cpp-compatible runners, KoboldCpp, text-generation-webui, and similar local model tools.
Start simple
Start with Q4_K_M unless you know your machine has enough memory for larger variants.
Raise quality
Use Q5_K_M or Q6_K when you want stronger output quality and can spend more memory.
Reference use
Use Q8_0 only for capable hardware, archival, conversion, or reference workflows.
Hugging Face
Repository and model cards
All current model files and release metadata are published in one repository, including sizes, checksums, and direct download links.
Available files
Qwen 9B PowerBASIC GGUF variants
Hosted on Hugging Face: https://huggingface.co/Theogott/pb-qwen3_5-9b-powerbasic-ggufs
Balanced~6.47 GB
Q5_K_M
A strong middle ground with better output quality while staying manageable on many local AI setups.
PB_qwen3_5_9b_dora-Q5_K_M.gguf
Higher quality~7.36 GB
Q6_K
Use this when you can spend more memory for stronger answers and more stable code-oriented behavior.
PB_qwen3_5_9b_dora-Q6_K.gguf
High precision~9.53 GB
Q8_0
For capable hardware where quality matters more than download size and runtime memory footprint.
PB_qwen3_5_9b_dora-Q8_0.gguf
Highest precision~15.34 GB
BF16
Use this when you want higher arithmetic precision for advanced coding workflows, heavy instruction editing, or conversion and benchmark experiments.
PB_qwen3_5_9b_dora-F16.gguf
Now available
SPR Models
Hosted on Hugging Face: https://huggingface.co/Theogott/pb-qwen3_5-9b-powerbasic-ggufs
SPR GGUF~4+ GB
Q4_K_M
SPR variant tuned for PowerBASIC-oriented instruction tuning and local automation use-cases.
spr_qwen3_5_9b_dora_q4_k_m.gguf
SPR GGUF~4+ GB
Q4_K_M VRAM-safe
VRAM-safe variant with same token-space structure plus a safer memory footprint.
spr_qwen3_5_9b_dora_vramsafe_q4_k_m.gguf
SPR GGUF~5+ GB
Q6_K VRAM-safe
Higher precision while keeping memory pressure manageable.
spr_qwen3_5_9b_dora_vramsafe_q6_k.gguf
SPR GGUF~5+ GB
Q8_0 VRAM-safe
For stronger output quality in local runtimes with enough memory available.
spr_qwen3_5_9b_dora_vramsafe_q8_0.gguf
SPR GGUF~6+ GB
BF16 VRAM-safe
Higher precision variant for advanced inference and conversion workflows.
spr_qwen3_5_9b_dora_vramsafe_bf16.gguf