Qwen 3.5 4B

Model profile
Model	Size	Approximate size
Qwen 3.5 4BModel source: provider262,144 tokens max native context	4B	2.4 GB4-bit quantization

Compatible hardware Estimated speeds, not benchmark results: calculated from memory bandwidth and model size. Real results can differ significantly because there is no precise formula for deriving LLM generation speed from hardware specifications alone.
Hardware	Memory	Bandwidth	vLLM	Estimated generation
DDR4 16GB Computer	16 GBRAM	51.2 GB/s	no	11 tok/s4-bit quantization
DDR5 16GB Computer	16 GBRAM	89.6 GB/s	no	20 tok/s4-bit quantization
DDR5 32GB Computer	32 GBRAM	89.6 GB/s	no	20 tok/s4-bit quantization
Mac mini M4	24 GBUnified RAM	120 GB/s	no	26 tok/s4-bit quantization
RTX 2000 Ada	16 GBGPU VRAM	224 GB/s	yes	49 tok/s4-bit quantization
Radeon 8060S 96GB	96 GBUnified RAM	256 GB/s	yes	56 tok/s4-bit quantization
M4 Pro	24 GBUnified RAM	273 GB/s	no	59 tok/s4-bit quantization
DGX Spark	128 GBUnified RAM	273 GB/s	yes	59 tok/s4-bit quantization
RTX 4060 Ti 16GB	16 GBGPU VRAM	288 GB/s	yes	62 tok/s4-bit quantization
M5 Pro	64 GBUnified RAM	307 GB/s	no	66 tok/s4-bit quantization
RTX 3060 12GB	12 GBGPU VRAM	360 GB/s	yes	77 tok/s4-bit quantization
RTX 5060 Ti 16GB	16 GBGPU VRAM	448 GB/s	yes	95 tok/s4-bit quantization
M5 Max	128 GBUnified RAM	614 GB/s	no	127 tok/s4-bit quantization
M3 Ultra	96 GBUnified RAM	819 GB/s	no	164 tok/s4-bit quantization
RTX 5080	16 GBGPU VRAM	960 GB/s	yes	188 tok/s4-bit quantization
RTX 3090 Ti	24 GBGPU VRAM	1008 GB/s	yes	196 tok/s4-bit quantization
M5 Ultra	256 GBUnified RAM	1200 GB/s	no	227 tok/s4-bit quantization
RTX 5090	32 GBGPU VRAM	1792 GB/s	yes	313 tok/s4-bit quantization
RTX PRO 6000	96 GBGPU VRAM	1792 GB/s	yes	313 tok/s4-bit quantization
DGX H200	1128 GBGPU HBM3e	4800 GB/s	yes	602 tok/s4-bit quantization
DGX Station	748 GBCoherent Memory	7100 GB/s	yes	732 tok/s4-bit quantization
ET900N G3	748 GBCoherent Memory	7100 GB/s	yes	732 tok/s4-bit quantization
DGX B200	1440 GBGPU HBM3e	8000 GB/s	yes	771 tok/s4-bit quantization
GB200 NVL72	13400 GBGPU HBM3e	8000 GB/s	yes	771 tok/s4-bit quantization
GB300 NVL72	20000 GBGPU HBM3e	8000 GB/s	yes	771 tok/s4-bit quantization

2 videos found Showing 1-2

Video Execute Automation 2026-09-11

I Built an Auto Router for Local LLMs with LiteLLM + Pi Coding Agent

Demonstrates LiteLLM Auto Router with Pi Coding Agent, Ollama, and oMLX on Apple Silicon, comparing heuristic versus LLM classifiers for Qwen3.5 4B, Gemma 4, and Qwen3.8 27B.

Lessons learned Gemma 4 26B Qwen 3.8 27B Qwen 3.5 4B

Video Unbiased Bob 2026-07-27

Evaluating ~3-4B parameter LLMs. Nanbeige/Qwen/LocoOperator/Llama/Opus finetunes.

Qwen 3.5 4b remains the best 4 billion parameter model among Nanbeige, Qwen, LocoOperator, Llama and Opus finetunes.

Llama 3.2 3B Instruct Ministral 3 3B Qwen 3.5 4B Nanbeige 4.2 3B

LLM model: Qwen 3.5 4B

I Built an Auto Router for Local LLMs with LiteLLM + Pi Coding Agent

Evaluating ~3-4B parameter LLMs. Nanbeige/Qwen/LocoOperator/Llama/Opus finetunes.