Welcome! Type "help" for available commands.

$

Welcome! Type "help" for available commands.

$

Welcome! Type "help" for available commands.

$

~/bookmarks

A collection of bookmarks filtered by the tag "LLM Inference".

Filter by:

Showing 1-19 of 19 bookmarks tagged with "LLM Inference"

All Stories

github.com

GitHub - warpfront/hipfire: RDNA-native LLM inference engine in Rust.

LLM Inference Speculative Decoding Model Quantization

Oct 1, 2026

github.com

GitHub - MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark: Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)

LLM Inference Qwen3.8-Flash-Next Vision-Language Model

Sep 19, 2026

huggingface.co

harshatheg/Qwen-2.5-1B-RLCD · Hugging Face

LLM Inference Apple Silicon Parallel Constrained Decoding

Sep 16, 2026

github.com

GitHub - bilikaz/qwen38-flash-next-recipe: qwen38-flash-next recipe for solo GB10

Qwen LLM Inference Speculative Decoding

Sep 14, 2026

mmoustafa.com

So you want to use OpenRouter? — Mo Moustafa

LLM Inference OpenRouter AI Model Providers

Sep 11, 2026

perplexity.ai

Optimizing On-Device Inference for Apple Silicon

Mixture-of-Experts LLM Inference Apple Silicon

Sep 3, 2026

github.com

GitHub - quimmedes/cafe-llama.cpp: A experimental fork of llama.cpp with LLM...

Mixture-of-Experts LLM Inference Speculative Decoding

Aug 30, 2026

github.com

GitHub - LaurentZuijdwijk/llama.cpp: llama.cpp with adaptive speculative decoding (--spec-draft-adaptive) and...

LLM Inference Vulkan Speculative Decoding

Aug 29, 2026

github.com

feat(qwen4_exp): support Qwen3.8-Flash-Next by jason-fxz · Pull Request #257 ·...

Qwen Mixture-of-Experts LLM Inference

Aug 29, 2026

huggingface.co

The V100 Homelab Field Guide - a Hugging Face Space...

LLM Inference Token Throughput Tesla V100

Aug 29, 2026

kyuz0.github.io

AMD Strix Halo — Backend Benchmarks (Grid View)

LLM Inference Vulkan Model Quantization

Aug 26, 2026

huggingface.co

froggeric/Qwen-Fixed-Chat-Templates · Hugging Face

Qwen LLM Inference Jinja Chat Templates

Aug 19, 2026

huggingface.co

z-lab/Qwen3.6-27B-DFlash · Hugging Face

LLM Inference Qwen3.6-27B DFlash

Aug 8, 2026

x.com

Gemma 4 26B A4B MoE - 500+ t/s decode -...

LLM Inference KV Cache Quantization Continuous Batching

Aug 1, 2026

fireworks.ai

Fireworks AI - Fastest Inference for Generative AI

LLM Inference Generative AI AI Infrastructure

Jun 9, 2026

github.com

GitHub - QuinsZouls/llama-cpp-turboquant at llama-next

LLM Inference C/C++ Implementation Model Quantization

May 9, 2026

github.com

GitHub - Luce-Org/lucebox-hub: Lucebox optimization hub: hand-tuned LLM inference, built...

LLM Inference RTX 3090 Quantization Kernels

May 3, 2026

github.com

GitHub - ubergarm/llama.cpp at ug/port-sweep-bench

LLM Inference C/C++ Implementation Quantization Techniques

Mar 31, 2026

linkedin.com

Running 122B-Parameter LLMs Locally on AMD Strix Halo for OpenClaw:...

LLM Inference Local LLMs AMD Strix Halo

Mar 21, 2026

A collection of bookmarks filtered by the tag "LLM Inference".

Filter by:

Showing 1-19 of 19 bookmarks tagged with "LLM Inference"

All Stories

github.com

GitHub - warpfront/hipfire: RDNA-native LLM inference engine in Rust.

LLM Inference Speculative Decoding Model Quantization

Oct 1, 2026

github.com

GitHub - MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark: Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)

LLM Inference Qwen3.8-Flash-Next Vision-Language Model

Sep 19, 2026

huggingface.co

harshatheg/Qwen-2.5-1B-RLCD · Hugging Face

LLM Inference Apple Silicon Parallel Constrained Decoding

Sep 16, 2026

github.com

GitHub - bilikaz/qwen38-flash-next-recipe: qwen38-flash-next recipe for solo GB10

Qwen LLM Inference Speculative Decoding

Sep 14, 2026

mmoustafa.com

So you want to use OpenRouter? — Mo Moustafa

LLM Inference OpenRouter AI Model Providers

Sep 11, 2026

perplexity.ai

Optimizing On-Device Inference for Apple Silicon

Mixture-of-Experts LLM Inference Apple Silicon

Sep 3, 2026

github.com

GitHub - quimmedes/cafe-llama.cpp: A experimental fork of llama.cpp with LLM...

Mixture-of-Experts LLM Inference Speculative Decoding

Aug 30, 2026

github.com

GitHub - LaurentZuijdwijk/llama.cpp: llama.cpp with adaptive speculative decoding (--spec-draft-adaptive) and...

LLM Inference Vulkan Speculative Decoding

Aug 29, 2026

github.com

feat(qwen4_exp): support Qwen3.8-Flash-Next by jason-fxz · Pull Request #257 ·...

Qwen Mixture-of-Experts LLM Inference

Aug 29, 2026

huggingface.co

The V100 Homelab Field Guide - a Hugging Face Space...

LLM Inference Token Throughput Tesla V100

Aug 29, 2026

kyuz0.github.io

AMD Strix Halo — Backend Benchmarks (Grid View)

LLM Inference Vulkan Model Quantization

Aug 26, 2026

huggingface.co

froggeric/Qwen-Fixed-Chat-Templates · Hugging Face

Qwen LLM Inference Jinja Chat Templates

Aug 19, 2026

huggingface.co

z-lab/Qwen3.6-27B-DFlash · Hugging Face

LLM Inference Qwen3.6-27B DFlash

Aug 8, 2026

x.com

Gemma 4 26B A4B MoE - 500+ t/s decode -...

LLM Inference KV Cache Quantization Continuous Batching

Aug 1, 2026

fireworks.ai

Fireworks AI - Fastest Inference for Generative AI

LLM Inference Generative AI AI Infrastructure

Jun 9, 2026

github.com

GitHub - QuinsZouls/llama-cpp-turboquant at llama-next

LLM Inference C/C++ Implementation Model Quantization

May 9, 2026

github.com

GitHub - Luce-Org/lucebox-hub: Lucebox optimization hub: hand-tuned LLM inference, built...

LLM Inference RTX 3090 Quantization Kernels

May 3, 2026

github.com

GitHub - ubergarm/llama.cpp at ug/port-sweep-bench

LLM Inference C/C++ Implementation Quantization Techniques

Mar 31, 2026

linkedin.com

Running 122B-Parameter LLMs Locally on AMD Strix Halo for OpenClaw:...

LLM Inference Local LLMs AMD Strix Halo

Mar 21, 2026

~/bookmarks

GitHub - warpfront/hipfire: RDNA-native LLM inference engine in Rust.

GitHub - MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark: Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)

harshatheg/Qwen-2.5-1B-RLCD · Hugging Face

GitHub - bilikaz/qwen38-flash-next-recipe: qwen38-flash-next recipe for solo GB10

So you want to use OpenRouter? — Mo Moustafa

Optimizing On-Device Inference for Apple Silicon

GitHub - quimmedes/cafe-llama.cpp: A experimental fork of llama.cpp with LLM...

GitHub - LaurentZuijdwijk/llama.cpp: llama.cpp with adaptive speculative decoding (--spec-draft-adaptive) and...

feat(qwen4_exp): support Qwen3.8-Flash-Next by jason-fxz · Pull Request #257 ·...

The V100 Homelab Field Guide - a Hugging Face Space...

AMD Strix Halo — Backend Benchmarks (Grid View)

froggeric/Qwen-Fixed-Chat-Templates · Hugging Face

z-lab/Qwen3.6-27B-DFlash · Hugging Face

Gemma 4 26B A4B MoE - 500+ t/s decode -...

Fireworks AI - Fastest Inference for Generative AI

GitHub - QuinsZouls/llama-cpp-turboquant at llama-next

GitHub - Luce-Org/lucebox-hub: Lucebox optimization hub: hand-tuned LLM inference, built...

GitHub - ubergarm/llama.cpp at ug/port-sweep-bench

Running 122B-Parameter LLMs Locally on AMD Strix Halo for OpenClaw:...

Discover More

hipfire-models/qwen3.8-27b · Hugging Face

GitHub - julianmb/halofpx: High-performance Lemonade alternative for AMD Strix Halo & Radeon — latest MoE models (Ling-3.0-Flash, Qwen 3.8 Flash Next, Ornith 1.5), bleeding-edge RDNA 3.5 Wave64/ROCmFP4 kernels, and silicon-tuned profiles.

vmlinux/Muse-Glimmer-30B-ROCmFPX-GGUF · Hugging Face

Similar Content

GitHub - warpfront/hipfire: RDNA-native LLM inference engine in Rust.

GitHub - MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark: Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)

harshatheg/Qwen-2.5-1B-RLCD · Hugging Face

GitHub - bilikaz/qwen38-flash-next-recipe: qwen38-flash-next recipe for solo GB10

So you want to use OpenRouter? — Mo Moustafa

Optimizing On-Device Inference for Apple Silicon

GitHub - quimmedes/cafe-llama.cpp: A experimental fork of llama.cpp with LLM...

GitHub - LaurentZuijdwijk/llama.cpp: llama.cpp with adaptive speculative decoding (--spec-draft-adaptive) and...

feat(qwen4_exp): support Qwen3.8-Flash-Next by jason-fxz · Pull Request #257 ·...

The V100 Homelab Field Guide - a Hugging Face Space...

AMD Strix Halo — Backend Benchmarks (Grid View)

froggeric/Qwen-Fixed-Chat-Templates · Hugging Face

z-lab/Qwen3.6-27B-DFlash · Hugging Face

Gemma 4 26B A4B MoE - 500+ t/s decode -...

Fireworks AI - Fastest Inference for Generative AI

GitHub - QuinsZouls/llama-cpp-turboquant at llama-next

GitHub - Luce-Org/lucebox-hub: Lucebox optimization hub: hand-tuned LLM inference, built...

GitHub - ubergarm/llama.cpp at ug/port-sweep-bench

Running 122B-Parameter LLMs Locally on AMD Strix Halo for OpenClaw:...

Discover More

hipfire-models/qwen3.8-27b · Hugging Face

GitHub - julianmb/halofpx: High-performance Lemonade alternative for AMD Strix Halo & Radeon — latest MoE models (Ling-3.0-Flash, Qwen 3.8 Flash Next, Ornith 1.5), bleeding-edge RDNA 3.5 Wave64/ROCmFP4 kernels, and silicon-tuned profiles.

vmlinux/Muse-Glimmer-30B-ROCmFPX-GGUF · Hugging Face