Qwen3.6 28B — Hardware Requirements & GPU Compatibility
Chat
Qwen3.6 28B is a 28.2B-parameter open language model from 0xSero in the Qwen family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 17.33 GB of VRAM — see which GPUs and Macs can run it below.
1.2K downloads
27 likesSpecifications
- Publisher
- 0xSero
- Family
- Qwen
- Parameters
- 28.2B
- Architecture
- Qwen3_5MoeForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-05-30
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Qwen3.6 28B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 12.4 GB | 23.0 GB | 12.00 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 12.7 GB | 23.4 GB | 12.35 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 14.2 GB | 24.8 GB | 13.77 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 17.3 GB | 28.0 GB | 16.94 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 20.5 GB | 31.2 GB | 20.12 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 23.7 GB | 34.3 GB | 23.30 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 28.6 GB | 39.3 GB | 28.24 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Qwen3.6 28B?
Q4_K_M · 17.3 GBQwen3.6 28B (Q4_K_M) requires 17.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 23+ GB is recommended. Using the full 262K context window can add up to 10.7 GB, bringing total usage to 28.0 GB. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Qwen3.6 28B?
Q4_K_M · 17.3 GB21 devices with unified memory can run Qwen3.6 28B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Qwen3.6 28B need?
Qwen3.6 28B requires 17.3 GB of VRAM at Q4_K_M, or 28.6 GB at Q8_0. Full 262K context adds up to 10.7 GB (28.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 28.2B × 4.8 bits ÷ 8 = 16.9 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 11.1 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M17.3 GBQ4_K_M + full context28.0 GB- Can NVIDIA GeForce RTX 4090 run Qwen3.6 28B?
Yes, at Q6_K (23.7 GB) or lower. Higher quantizations like Q8_0 (28.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Qwen3.6 28B?
For Qwen3.6 28B, Q4_K_M (17.3 GB) offers the best balance of quality and VRAM usage. Q5_K_S (19.8 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XXS at 11.3 GB.
VRAM requirement by quantization
IQ3_XXS11.3 GBQ3_K_M14.2 GBQ4_K_S16.3 GBQ4_K_M ★17.3 GBQ5_K_M20.5 GBQ8_028.6 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwen3.6 28B on a Mac?
Qwen3.6 28B requires at least 11.3 GB at IQ3_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Qwen3.6 28B locally?
Yes — Qwen3.6 28B can run locally on consumer hardware. At Q4_K_M quantization it needs 17.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen3.6 28B?
At Q4_K_M, Qwen3.6 28B can reach ~168 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~38 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 17.3 × 0.55 = ~168 tok/s
Estimated speed at Q4_K_M (17.3 GB)
~168 tok/s~38 tok/s~126 tok/s~104 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwen3.6 28B?
At Q4_K_M, the download is about 16.94 GB. The full-precision Q8_0 version is 28.24 GB. The smallest option (IQ3_XXS) is 10.94 GB.
- Which GPUs can run Qwen3.6 28B?
6 consumer GPUs can run Qwen3.6 28B at Q4_K_M (17.3 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Qwen3.6 28B?
21 devices with unified memory can run Qwen3.6 28B at Q4_K_M (17.3 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.