Frequently Asked Questions

“Backend library is not loaded” error

Problem: You see the error “Backend library is not loaded. Please run install_localLLM() first.”

Solution: Run the installation function after loading the package:

library(localLLM)
install_localLLM()

This downloads the platform-specific backend library. You only need to do this once.

Installation fails on my platform

Problem: install_localLLM() fails to download or install.

Solution: Check your platform is supported: - Windows (x86-64) - macOS (ARM64 / Apple Silicon) - Linux (x86-64)

If you’re on an unsupported platform, you may need to compile llama.cpp manually.

“Library already installed” but functions don’t work

Problem: install_localLLM() says the library is installed, but generation fails.

Solution: Try reinstalling:

# Force reinstall
install_localLLM(force = TRUE)

# Verify installation
lib_is_installed()

“Download lock” or “Another download in progress” error

Problem: A previous download was interrupted and left a lock file.

Solution: Clear the cache directory:

cache_root <- tools::R_user_dir("localLLM", which = "cache")
models_dir <- file.path(cache_root, "models")
unlink(models_dir, recursive = TRUE, force = TRUE)

Then try downloading again.

Download times out or fails

Problem: Large model downloads fail partway through.

Solution: 1. Check your internet connection 2. Try a smaller model first 3. Download manually and load from local path:

# Download with browser or wget, then:
model <- model_load("/path/to/downloaded/model.gguf")

“Model not found” when using cached model

Problem: You’re trying to load a model by name but it’s not found.

Solution: Check what’s actually cached:

cached <- list_cached_models()
print(cached)

Use the exact filename or a unique substring that matches only one model.

Private Hugging Face model fails

Problem: Downloading a gated/private model fails with authentication error.

Solution: Set your Hugging Face token:

# Get token from https://huggingface.co/settings/tokens
set_hf_token("hf_your_token_here")

# Now download should work
model <- model_load("https://huggingface.co/private/model.gguf")

R crashes when loading a model

Problem: R crashes or freezes when calling model_load().

Solution: The model is too large for your available RAM. Try:

1. Use a smaller quantized model (Q4 instead of Q8)
2. Free up memory by closing other applications
3. Check model requirements:

hw <- hardware_profile()
cat("Available RAM:", hw$ram_gb, "GB\n")

“Memory check failed” warning

Problem: localLLM warns about insufficient memory.

Solution: The safety check detected potential issues. Options:

1. Use a smaller model

2. Reduce context size:

   ctx <- context_create(model, n_ctx = 512)  # Smaller context

3. If you’re sure you have enough memory, proceed when prompted

Context creation fails with large n_ctx

Problem: Creating a context with large n_ctx fails.

Solution: Reduce the context size or use a smaller model:

# Instead of n_ctx = 32768, try:
ctx <- context_create(model, n_ctx = 4096)

GPU not being used

Problem: Generation is slow even with n_gpu_layers = 999.

Solution: Check if GPU is detected:

hw <- hardware_profile()
print(hw$gpu)

If no GPU is listed, the backend may not support your GPU. Currently supported: - NVIDIA GPUs (via CUDA) - Apple Silicon (Metal)

“CUDA out of memory” error

Problem: GPU runs out of memory during generation.

Solution: Reduce GPU layer count:

# Offload fewer layers to GPU
model <- model_load("model.gguf", n_gpu_layers = 20)

Output is garbled or nonsensical

Problem: The model produces meaningless text.

Solution: 1. Ensure you’re using a chat template:

messages <- list(
  list(role = "user", content = "Your question")
)
prompt <- apply_chat_template(model, messages)
result <- generate(ctx, prompt)

2. The model file may be corrupted - redownload it

Output contains strange tokens like <|eot_id|>

Problem: Output includes control tokens.

Solution: Use the clean = TRUE parameter:

result <- generate(ctx, prompt, clean = TRUE)
# or
result <- quick_llama("prompt", clean = TRUE)

Generation stops too early

Problem: Output is cut off before completion.

Solution: Increase max_tokens:

result <- quick_llama("prompt", max_tokens = 500)

Same prompt gives different results

Problem: Running the same prompt twice gives different outputs.

Solution: Set a seed for reproducibility:

result <- quick_llama("prompt", seed = 42)

With temperature = 0 (default), outputs should be deterministic.

Generation is very slow

Problem: Text generation takes much longer than expected.

Solutions:

1. Use GPU acceleration:

   model <- model_load("model.gguf", n_gpu_layers = 999)

2. Use a smaller model: Q4 quantization is faster than Q8

3. Reduce context size:

   ctx <- context_create(model, n_ctx = 512)

4. Use parallel processing for multiple prompts:

   results <- quick_llama(c("prompt1", "prompt2", "prompt3"))

Parallel processing isn’t faster

Problem: generate_parallel() is no faster than sequential generation.

Solution: Ensure n_seq_max is set appropriately:

ctx <- context_create(
  model,
  n_ctx = 2048,
  n_seq_max = 10  # Allow 10 parallel sequences
)

“GGUF format required” error

Problem: Trying to load a non-GGUF model.

Solution: localLLM only supports GGUF format. Convert your model or find a GGUF version on Hugging Face (search for “model-name gguf”).

Model works in Ollama but not localLLM

Problem: An Ollama model doesn’t work when loaded directly.

Solution: Use the Ollama integration:

# List available Ollama models
list_ollama_models()

# Load via Ollama reference
model <- model_load("ollama:model-name")