Text Generation
GGUF
English
Italian
llama.cpp
llm
local-llm
local-inference
inference-engine
runtime
llama-cpp
llamacpp
quantization
Mixture of Experts
mixture-of-experts
offloading
model-offloading
memory-offloading
storage-streaming
weight-streaming
disk-offload
nvme
ssd
multi-ssd
raid
prefetch
kv-cache
hierarchical-cache
sharding
model-sharding
tensor-parallelism
benchmark
benchmarking
profiling
performance
telemetry
hardware-detection
gpu
vulkan
cuda
rocm
hip
metal
amd
nvidia
intel
cpu-inference
consumer-hardware
low-vram
large-models
70b
120b
300b
400b
600b
1t
kimi-k2
deepseek
qwen3
llama4
glm
gpt-oss
openai-api
openai-compatible
ollama
ollama-compatible
api-server
rest-api
ide-integration
cline
continue
vscode
copilot-alternative
self-hosted
offline
privacy
local-first
on-premise
typescript
nodejs
react
desktop-app
cross-platform
windows
linux
macos
open-source
model-catalog
model-downloader
resumable-download
Ctrl+K