Run Qwen 3.5/3.6 35B on 8GB VRAM | LM Studio + Opencode Setup (40 tk /s)

UPDATE: This will also work with the new Qwen 3.6 models! Waffle ends at 1:35, 1.5x speed recommended. Run large models on cheap GPUs. This model is on-par with Claude Haiku 4.5, and can run on cheap consumer hardware! Setup guide for LM Studio + Opencode. You can also use ollama. https://qwen.ai/blog?id=qwen3.5

Join Today
[RANKING] 20 Local AI Models — 8GB VRAM Tier List (Qwen3.5, Gemma 4, DeepSeek)
▶︎

[RANKING] 20 Local AI Models — 8GB VRAM Tier List (Qwen3.5, Gemma 4, DeepSeek)

Running a 35B AI Model on 6GB VRAM, FAST (llama.cpp Guide)
▶︎

Running a 35B AI Model on 6GB VRAM, FAST (llama.cpp Guide)

The Best Local Agentic Coding Workflow (Complete Guide)
▶︎

The Best Local Agentic Coding Workflow (Complete Guide)

I ran Qwen 3.6 35B on 8GB of VRAM at almost 20 t/s (COMPLETE TUTORIAL using llama.cpp)
▶︎

I ran Qwen 3.6 35B on 8GB of VRAM at almost 20 t/s (COMPLETE TUTORIAL using llama.cpp)

Claude Code + LM Studio + Qwen3.5 35B A3B
▶︎

Claude Code + LM Studio + Qwen3.5 35B A3B

How much difference does MTP make? Qwen 3.6 27B tested - 16GB Local LLM setup
▶︎

How much difference does MTP make? Qwen 3.6 27B tested - 16GB Local LLM setup

Can Qwen Dethrone Opus 4.7, GPT 5.5 and Gemini 3.1?
▶︎

Can Qwen Dethrone Opus 4.7, GPT 5.5 and Gemini 3.1?

Your local LLM is 10x slower than it should be
▶︎

Your local LLM is 10x slower than it should be

GLM-5.2 vs Opus 4.8: Have Open Source Models Caught Up?
▶︎

GLM-5.2 vs Opus 4.8: Have Open Source Models Caught Up?

China’s Secret | The Most Unbelievable Megaprojects in China | 4K Travel Documentary
▶︎

China’s Secret | The Most Unbelievable Megaprojects in China | 4K Travel Documentary

The Local AI Hardware Mistake Everyone Makes
▶︎

The Local AI Hardware Mistake Everyone Makes

BitNet b1.58 How 1.58-Bit Ternary Weights Run LLMs on CPUs Without GPUs
▶︎

BitNet b1.58 How 1.58-Bit Ternary Weights Run LLMs on CPUs Without GPUs

How DeepSeek V4 fits on a laptop and what does it mean to us?
▶︎

How DeepSeek V4 fits on a laptop and what does it mean to us?

Ollama vs LM Studio vs llama.cpp: Which Should You Use?
▶︎

Ollama vs LM Studio vs llama.cpp: Which Should You Use?

Testing Qwen3.6 35B A3B with OpenCode on the M5 Pro
▶︎

Testing Qwen3.6 35B A3B with OpenCode on the M5 Pro

Gemma 4 26B vs 8GB VRAM! Abliterated LM Studio Guide 🤯
▶︎

Gemma 4 26B vs 8GB VRAM! Abliterated LM Studio Guide 🤯

DFlash on GTX 1060: Can Dense AI Models Cheat VRAM Like MoE?
▶︎

DFlash on GTX 1060: Can Dense AI Models Cheat VRAM Like MoE?

AMD MI50 32GB for Local AI: Qwen 3.6 & Gemma 4 on llama.cpp / vLLM (vs R9700)
▶︎

AMD MI50 32GB for Local AI: Qwen 3.6 & Gemma 4 on llama.cpp / vLLM (vs R9700)

Best Local Coding AI for 8GB VRAM (2026 Benchmark)
▶︎

Best Local Coding AI for 8GB VRAM (2026 Benchmark)

Every Way To Run Open Source AI Models
▶︎

Every Way To Run Open Source AI Models