Qwen3.6 40B Deckard MTP — Hardware Requirements & GPU Compatibility
ChatVision
Qwen3.6 40B Deckard MTP is a 40B-parameter open language model from PiehSoft in the Qwen 3.6 family. At Q4_K_M it needs about 26.40 GB of VRAM — see which GPUs and Macs can run it below.
Decent on a 24 GB GPU
Runs on 24 GB (Q2_K · ~35 tok/s · 16K)Macs from 32 GB (Q4_K_M · ~11 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen3.6 40B Deckard MTP
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve PiehSoft/Qwen3.6-40B-Deckard-MTP --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX A6000 (48 GB) (17 GB headroom) · Q4_K_M
- Generation speed
- ~19 tok/s
- generation speed
- Cost per 1M output tokens
- $4.85
- per 1M output tokens
How Much VRAM Does Qwen3.6 40B Deckard MTP Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 18.7 GB | 27.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 16K context · ~35 tok/s | |
| 21.4 GB | 30.1 GB | 3-bit medium — 3-bit medium quantization | Fits: 8K context · ~31 tok/s | |
| 26.4 GB | 35 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Does not fit: needs 30.4 GB | |
| 31.4 GB | 40 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 35.4 GB | |
| 36.3 GB | 44.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 40.3 GB | |
| 44 GB | 52.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 48 GB | |
| 88 GB | 96.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 92 GB |
Selected Q4_K_M
4-bit medium quantization30.4GBat 16K context
- Weights
- 25.5 GB
- KV cache
- 4.6 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 6.4 GB more, Q2_K fits
≥30 tok/s needs ≥1.22 TB/s · RTX 5090 ~44
Which Hardware Can Run Qwen3.6 40B Deckard MTP?
Q4_K_M · 26.4 GBQwen3.6 40B Deckard MTP (Q4_K_M) requires 26.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 35+ GB is recommended. 1 GPU can run it, including NVIDIA GeForce RTX 5090. 97 devices with unified memory can run Qwen3.6 40B Deckard MTP, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M5 Max (36 GB).
≤ 20 GB
≤ 20 GB tier →doesn't fit · smallest quant needs 22.7 GB
32–40 GB
fits · 1.6 GB free · up to 16K ctx
1 GPU · 3 Mac classes · 1 device family
RTX 5090~44Simulate output on RTX 5090M5 Max36 GB~12Simulate output on Mac Studio M5 Max (36 GB)M532 GB~4Simulate output on MacBook Air 13" M5 (32 GB)Orin~5Simulate output on NVIDIA Jetson AGX Orin 32GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Qwen3.6 40B Deckard MTP
Qwen 3.6 family · 15 models →Similar models
3| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Phi 3.5 MoE InstructMicrosoft | — | 23.9 GB | ~141 | same size |
| Falcon 40B InstructTII UAE | — | 23.8 GB | ~33 | same size |
| K2 Horizon MoVA 36B A4BIFM | — | 23.4 GB | ~162 | same size |
Specifications
- Publisher
- PiehSoft
- Family
- Qwen 3.6
- Parameters
- 40B
- Release Date
- 2026-05-28
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3.6 40B Deckard MTP need?
Qwen3.6 40B Deckard MTP requires 26.4 GB of VRAM at Q4_K_M, or 88 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 40B × 4.8 bits ÷ 8 = 24 GB
KV Cache + Overhead ≈ 2.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Qwen3.6 40B Deckard MTP?
Yes, at Q3_K_M (21.4 GB) or lower. Higher quantizations like Q4_K_M (26.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Qwen3.6 40B Deckard MTP?
For Qwen3.6 40B Deckard MTP, Q4_K_M (26.4 GB) offers the best balance of quality and VRAM usage. Q5_K_M (31.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 18.7 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3.6 40B Deckard MTP on a Mac?
Yes — Mac Studio M1 Max (32 GB) and 84 other Macs can run Qwen3.6 40B Deckard MTP. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 26.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run Qwen3.6 40B Deckard MTP locally?
Yes — Qwen3.6 40B Deckard MTP can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3.6 40B Deckard MTP?
At Q4_K_M, Qwen3.6 40B Deckard MTP can reach ~182 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 26.4 × 0.65 = ~197 tok/s
Estimated speed at Q4_K_M (26.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen3.6 40B Deckard MTP?
At Q4_K_M, the download is about 24.00 GB. The full-precision BF16 version is 80.00 GB. The smallest option (Q2_K) is 17.00 GB.
Which GPUs can run Qwen3.6 40B Deckard MTP?
1 consumer GPU can run Qwen3.6 40B Deckard MTP at Q4_K_M. Top options include NVIDIA GeForce RTX 5090.
Which devices can run Qwen3.6 40B Deckard MTP?
97 devices with unified memory can run Qwen3.6 40B Deckard MTP at Q4_K_M (26.4 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.