Model record
Qwen3.6 35B-A3B
Alibaba Cloud · Apache 2.0 · verified
What this model is
Qwen reports 35B total parameters and 3B activated parameters, with 8 routed experts plus 1 shared expert per token.
The architecture is mixture of experts. Memory must hold the full weight set, while active parameters affect the speed heuristic. Experts can be offloaded to system memory, but that trades speed for capacity.
Memory and quantization
Decimal GB. Sizes combine the published GGUF weight file with the F16 multimodal projector required for image and video input.
| Quantization | Published files | 8K estimate | Smallest comfortable GPU | Smallest comfortable Mac | Context at smallest GPU / Mac | Speed estimate | Run commands |
|---|---|---|---|---|---|---|---|
| MXFP4 | 22.61 GB | 24.27 GB | NVIDIA GeForce RTX 5090 32GB · 32 GB VRAM | Apple Mac mini M4 Pro 48GB · 48 GB unified memory | 262,144 / 262,144 tokens | Estimate · Fast relative class | ollama run qwen3.6:35b-a3b lms get "Qwen3.6 35B-A3B"@mxfp4 |
| Q4_K_M | 23.03 GB | 24.70 GB | NVIDIA GeForce RTX 5090 32GB · 32 GB VRAM | Apple Mac mini M4 Pro 48GB · 48 GB unified memory | 262,144 / 262,144 tokens | Estimate · Fast relative class | ollama run qwen3.6:35b-a3b-q4_K_M lms get "Qwen3.6 35B-A3B"@q4_k_m |
| Q8_0 | 37.80 GB | 39.47 GB | NVIDIA RTX 6000 Ada 48GB · 48 GB VRAM | Apple Mac mini M4 Pro 48GB · 48 GB unified memory | 262,144 / 262,144 tokens | Estimate · Fast relative class | ollama run qwen3.6:35b-a3b-q8_0 lms get "Qwen3.6 35B-A3B"@q8_0 |
Estimate formula: published weight files + 0.1678 GB per 8K tokens × context / 8K + 1.5 GB runtime overhead. Sizes are decimal GB, not GiB. At 8K context, the smallest listed build is about 24.3 GB before OS and application reserve.
Full-attention KV estimate from the public config. Ten of 40 layers use full attention; linear-attention state is small and excluded from this conservative per-token figure.
Ollama tags were checked against the linked Ollama library pages on 2026-11-02. LM Studio's lms get suffix selects a file when the search results expose that exact quantization; confirm the local key with lms ls.
KV method source: https://huggingface.co/Qwen/Qwen3.6-35B-A3B/raw/main/config.json
Speed heuristic
Not benchmarked here. The calculator uses 3B active parameters only as a relative speed heuristic.
Active path: 3B parameters. This is a relative speed signal only; it is not a tokens/sec benchmark.
If the full weights do not fit in accelerator memory but do fit in system memory, the calculator marks the result as a tight CPU-offload fit. Expect substantially slower generation and verify the runtime's MoE offload support.
Runtimes
- Ollama
- llama.cpp
- MLX
- vLLM
ollama run qwen3.6:35b-a3blms get "Qwen3.6 35B-A3B"@mxfp4
lms load <model-key-from-lms-ls> --gpu max --context-length 8192License restrictions
Apache 2.0 permits commercial use and modification; retain notices and comply with the patent and termination terms.
This is a plain-language summary, not legal advice. Read the linked license before commercial deployment or redistribution.
Known issues
- The native context is 262K tokens; long prompts can exhaust memory even when the quantized weights fit.
- The GGUF package needs the multimodal projector for vision and video input.
If it does not fit, try these smaller records
These alternatives have a lower recommended memory target in the current catalog. Open each page to compare the quantization-specific fit before downloading.
Qwen3.8 27B
Dense · starting at 20 GB
gpt-oss-20b
MoE · starting at 14 GB
Qwen3 8B
Dense · starting at 8 GB
DeepSeek R1 8B
Dense · starting at 8 GB
FAQ
Model-specific questions
What is the smallest local file for Qwen3.6 35B-A3B?
The smallest published weight package in this record is MXFP4 at 22.61 GB. The 8K runtime estimate adds 0.17 GB of KV cache and 1.5 GB overhead, for about 24.3 GB before operating-system reserve.
How much memory do the published quantizations need at 8K?
MXFP4 about 24.3 GB at 8K; Q4_K_M about 24.7 GB at 8K; Q8_0 about 39.5 GB at 8K. These are calculated estimates using the published weight sizes and the model's KV-cache assumption, not live memory measurements.
Which GPU and Mac configurations are comfortable for Qwen3.6 35B-A3B?
Against the current catalog, the smallest configurations that clear the 20% headroom target are: MXFP4: NVIDIA GeForce RTX 5090 32GB; Q4_K_M: NVIDIA GeForce RTX 5090 32GB; Q8_0: NVIDIA RTX 6000 Ada 48GB. A larger configuration may still be preferable for longer context or faster memory bandwidth.
What is the right Ollama or LM Studio command for Qwen3.6 35B-A3B?
Use the command attached to the specific quantization in the table. Ollama tags are taken from the checked Ollama library pages. For LM Studio, use lms get with the displayed quantization suffix, then load the resulting local key from lms ls with --gpu max and the desired context length.
What should I run instead if Qwen3.6 35B-A3B does not fit?
Smaller catalog alternatives include Qwen3.8 27B, gpt-oss-20b, Qwen3 8B, DeepSeek R1 8B. Compare their quantization tables and minimum memory before choosing; a smaller parameter count does not always mean a proportionally smaller download.
Sources
- https://huggingface.co/Qwen/Qwen3.6-35B-A3B
- https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF
- https://ollama.com/library/qwen3.6
- https://huggingface.co/Qwen/Qwen3.6-35B-A3B/raw/main/config.json
This page is an independent compatibility guide, not official documentation. Verify the primary source before downloading or deploying a model.