noonghunna writes a single-card RTX 3090 (24 GB) guide for local LLM inference, mapping which models and context lengths fit on one card, what can't be done, and the pitfalls that cause mid-session OOM crashes.
- A hardware cliff ("Cliff 2b") at ~21–26K accumulated tokens makes all single-card vLLM configs unsafe for agent-style workloads that retain context across turns.
- Qwen3.8-27B has an incubating single-card llama.cpp path at 262K context with vision (q4_0 KV + F16 mmproj), but it sits below the project's serving-grade KV floor.
- The 2026-08-12 retirement of all llama.cpp single-card slugs removed 200K context and ~60 TPS support for Qwen3.6-27B, leaving only a 32K, no-vision vLLM path at ~32 TPS.
- A hardware cliff ("Cliff 2b") at ~21–26K accumulated tokens makes all single-card vLLM configs unsafe for agent-style workloads that retain context across turns.
- Qwen3.8-27B has an incubating single-card llama.cpp path at 262K context with vision (q4_0 KV + F16 mmproj), but it sits below the project's serving-grade KV floor.
- The 2026-08-12 retirement of all llama.cpp single-card slugs removed 200K context and ~60 TPS support for Qwen3.6-27B, leaving only a 32K, no-vision vLLM path at ~32 TPS.
Thomas Joos writes that choosing LLM deployment now means picking between cloud APIs, datacenter GPUs or local workstations, with technical limits set by memory and bandwidth rather than raw compute and software choice tied to load profile. Quantization shrinks models to fit consumer GPUs and unified-memory systems, while token generation is bandwidth bound so bandwidth per dollar matters more than TFLOPS. Economically, self-hosting an eight-H100 cluster costs about $237k per year over three years versus higher on-demand cloud pricing, but break-even needs 50-83% sustained utilization that teams typically reach only 40-65%, and the strongest case for local inference is sovereignty and resilience not pure cost.
- Mistral Large 3 ships as a 675B-parameter mixture-of-experts with 41B active per token under Apache 2.0
- Nvidia DGX Spark offers 128 GB unified memory at $4,699 list price since Feb 23 2026
- vLLM generates 44x the tokens per second of llama.cpp at 64 concurrent users on H200 with Llama 3.1 8B
- DevTk finds self-hosting breaks even only at several billion tokens per month versus budget hosted open models
- Martin Kuppinger says sovereignty is not an end in itself; security and resilience come first and exit path matters more than immediate rebuild
- Mistral Large 3 ships as a 675B-parameter mixture-of-experts with 41B active per token under Apache 2.0
- Nvidia DGX Spark offers 128 GB unified memory at $4,699 list price since Feb 23 2026
- vLLM generates 44x the tokens per second of llama.cpp at 64 concurrent users on H200 with Llama 3.1 8B
- DevTk finds self-hosting breaks even only at several billion tokens per month versus budget hosted open models
- Martin Kuppinger says sovereignty is not an end in itself; security and resilience come first and exit path matters more than immediate rebuild
This guide helps engineers build and ship LLM products by covering the full technical stack. It moves from core mechanics (tokenization, embeddings, attention) to training methodologies (pretraining, SFT, RLHF/DPO) and deployment optimizations (LoRA, quantization, vLLM). The focus is on managing critical production tradeoffs between accuracy, latency, memory, and cost
Qwen3-Coder-Next is an 80B MoE model with 256K context designed for fast, agentic coding and local use. It offers performance comparable to models with 10-20x more active parameters and excels in long-horizon reasoning, complex tool use, and recovery from execution failures.
This blog post explains the causes of nondeterminism in LLM inference, arguing that it's not simply due to floating-point non-associativity and concurrency, but rather a lack of batch invariance in kernels. It details how to achieve batch invariance in RMSNorm, matrix multiplication, and attention, and presents experimental results demonstrating deterministic completions and the benefits for on-policy RL.
Running GenAI models is easy. Scaling them to thousands of users, not so much. This guide details avenues for scaling AI workloads from proofs of concept to production-ready deployments, covering API integration, on-prem deployment considerations, hardware requirements, and tools like vLLM and Nvidia NIMs.
K8S-native cluster-wide deployment for vLLM. Provides a reference implementation for building an inference stack on top of vLLM, enabling scaling, monitoring, request routing, and KV cache offloading with easy cloud deployment.
vLLM Production Stack provides a reference implementation on how to build an inference stack on top of vLLM, allowing for scalable, monitored, and performant LLM deployments using Kubernetes and Helm.
The article discusses the importance of fine-tuning machine learning models for optimal inference performance and explores popular tools like vLLM, TensorRT, ONNX Runtime, TorchServe, and DeepSpeed.
