largeApache 2.036B paramsOpen weights

Qwen3.6 35B (A3B)

36B parameter open-weight model. Sparse mixture-of-experts - 36B total across 256 experts with ~3B active per token. 256K context, image input, Apache 2.0. The Ollama Q4_K_M is ~24 GB, yet sparsity keeps it genuinely usable even heavily split: measured 32.8 tok/s on an RTX 3080 (10 GB) with only 35% of the model in VRAM (2026-08-01). The strongest capability-per-VRAM entry in the current catalog for machines with fast system RAM.

Alibaba · Qwen 3.6

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedJune 2026SourcesHuggingFace model card (Qwen/Qwen3.6-35B-A3B), official docs, OpenSourcesAI editorial review.

VRAM figures are empirical estimates. Actual usage varies by runtime, context length, and system configuration. Verify on your specific hardware before production use.

Will Qwen3.6 35B (A3B) run on your machine?

Qwen3.6 35B (A3B) is 36B parameters and needs 25.5 GB of VRAM at Q4_K_M — 24 GB of weights plus 1.5 GB of runtime overhead for the inference server itself.

VRAM by quantization

QuantizationWeightsNeeds (with overhead)Quality
Q4_K_M24 GB25.5 GBgood

Fit on common hardware at Q4_K_M

HardwareMemory the model can useSystem RAMVerdict
CPU OnlyNone (CPU only)16 GBToo large
RTX 4060 Laptop8 GB16 GBToo large
RTX 3060 (12GB)12 GB32 GBToo large
RTX 4060 Ti (16GB)16 GB32 GBToo large
RTX 309024 GB64 GBCPU offload
Apple Silicon (Unified Memory) 36 GB27 GB of 36 GB36 GBTight
RTX 509032 GB64 GBComfortable
Apple Silicon (Unified Memory) 48 GB36 GB of 48 GB48 GBComfortable
Apple Silicon (Unified Memory) 64 GB48 GB of 64 GB64 GBComfortable

Comfortable means VRAM clears the requirement by 2 GB or more. Tight means it covers the requirement with no margin. CPU offload means the model does not fit in VRAM but system RAM is at least 1.6× the weights, so it will run at reduced speed — expect roughly 1–5 tokens per second. Figures are weights plus a fixed runtime overhead and exclude KV-cache growth, which scales with context length.

Apple Silicon shares one pool of memory between the system and the GPU, so a model cannot use all of it. These rows apply the same 75% usable fraction the Compatibility Checker uses, which is why a 36 GB Mac is graded on less than 36 GB.

Check Qwen3.6 35B (A3B) against your exact hardwareHow these verdicts are calculated

Related models

Laguna XS 2.133.4B parameter model — shared focus: coding, agents, tool-use.Qwen2.5 32B32B parameter model — shared focus: chat, coding, reasoning.North Mini Code 1.030.5B parameter model — shared focus: coding, agents, tool-use.Qwen2.5 14BBuilders hosting local AI on a single RTX 4080 (16 GB) or RTX 4090 (24 GB) who want near-frontier multilingual reasoning, mathematical accuracy, and agentic coding performance without multi-GPU infrastructure. The sweet spot between consumer accessibility and frontier-class open-weight capability for 2026 local deployment.

Ready to run this model locally?

Find a compatible interface in our Local AI Tools directory →