Problemsby IbisRunning Claude Code locally hits memory and speed limits
MLOps3 posts from 3 people2d active+22 posts in the last 7 days, 0 the 7 days before (rising)
Posts per day
The posts behind it
3, newest firstMisc. bug: Anthropic /v1/messages drops output_config.effort### Name and Version version: 0.6.0-dev (build 11457, commit 5ad1c5da0) built with GNU 13.3.0 for Linux x86_64 The converter code is unchanged on current master (checked at `a0e6dc7384` on 2026-10-14). ### Operating systems Linux ### Which llama.cpp modules do you know to be...ggml-org/llama.cpp · goodbadwolfOpen ↗Misc. bug: llama-server Denial Of Service exchaust VRAM### Name and Version ./llama-server --version version: 0.6.0-dev (build 11646, commit 733f57a99) built with Clang 23.1.3 for FreeBSD amd64 ### Operating systems BSD ### Which llama.cpp modules do you know to be affected? llama-server ### Command line ### Problem description &...ggml-org/llama.cpp · vlforit6 repliesOpen ↗[Bug]: Humming FP8 linear crashes on per-tensor/per-channel FP8 weights, so FP8 models cannot start with VLLM_BATCH_INVARIANT=1 on Ampere### Your current environment Official image `vllm/vllm-openai:nightly-92044241a02f05de51420d654daf669de20b4691` on one NVIDIA A40 (SM86), run with the container's own environment. The output of python collect_env.py ### 🐛 Describe the bug When the Humming FP8 linear kernel is...vllm-project/vllm · ManfredssOpen ↗
Companies and products named
About this problem
Evidence
3 posts from 3 people in 2 places, about 2 a week over 10 days. Mostly on ggml-org/llama.cpp, vllm-project/vllm. Tools named alongside: OpenAI, llama.cpp, Qwen, vLLM.
Frustration Frustration 0 of 3· Seen on GitHub issues
How it was grouped
Posts that state a pain and match the "local-llm" rule about Claude Code. First post Oct 6, 2026, latest Oct 15, 2026. Corroborated: 3 or more posts from 2 or more people or places. Method
The same problem elsewhere
Running llama.cpp locally hits memory and speed limitsRunning Ollama locally hits memory and speed limitsRunning LLMs locally hits memory and speed limitsRunning Qwen locally hits memory and speed limitsRunning NVIDIA locally hits memory and speed limitsRunning Hugging Face locally hits memory and speed limitsRunning vLLM locally hits memory and speed limitsRunning OpenAI locally hits memory and speed limitsRunning PyTorch locally hits memory and speed limitsRunning GitHub locally hits memory and speed limitsRunning Mistral locally hits memory and speed limitsRunning DeepSeek locally hits memory and speed limits
Other Claude Code problems
Claude Code upgrades break working setupsClaude Code users keep filing bugsClaude Code error messages are crypticClaude Code GPU access and drivers are painfulFine-tuning Claude Code is costly and unpredictableTrouble with Claude Code browserTrouble with Claude Code sessionsClaude Code rate limits and usage caps block workClaude Code outages and slowdowns disrupt workTrouble with Claude Code desktopClaude Code runs out of context on real workClaude Code tables suffer from small files and skew
History
Running Claude Code locally hits memory and speed limits (3 posts)