Qwen 3.5 Sql 27B Distill 2B — Hardware Requirements & GPU Compatibility
ChatReasoning
Qwen 3.5 Sql 27B Distill 2B is a 27B-parameter open language model from AlioLeuchtmann in the Qwen 3.5 family. It supports a context window of up to 262,144 tokens. At BF16 it needs about 54.40 GB of VRAM — see which GPUs and Macs can run it below.
Qwen 3.5 Sql 27B Distill 2B runs on a 64 GB+ Mac or a workstation GPU
Best local pick → Mac Pro M2 Ultra (64 GB) · BF16 · 54.5 GB · ~10 tok/s
Macs from 64 GB (BF16 · ~10 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen 3.5 Sql 27B Distill 2B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve AlioLeuchtmann/qwen-3.5-sql-27B-Distill-2B --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on H100 (80 GB) (25 GB headroom) · BF16
- Generation speed
- ~40 tok/s
- generation speed
- Cost per 1M output tokens
- $18.63
- per 1M output tokens
How Much VRAM Does Qwen 3.5 Sql 27B Distill 2B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 54.4 GB | 54.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 54.5 GB |
Selected BF16
Brain floating point 1654.5GBat 16K context
- Weights
- 54.0 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 30.5 GB more
Or .
Which Hardware Can Run Qwen 3.5 Sql 27B Distill 2B?
BF16 · 54.4 GBQwen 3.5 Sql 27B Distill 2B (BF16) requires 54.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 71+ GB is recommended. Using the full 262K context window can add up to 3.1 GB, bringing total usage to 57.5 GB. No consumer GPU has enough memory. 52 devices with unified memory can run Qwen 3.5 Sql 27B Distill 2B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Pro M2 Ultra (64 GB).
64–80 GB
fits · 9.5 GB free · up to 256K ctx
3 Mac classes · 1 device family
M2 Ultra*64 GB~10Simulate output on Mac Pro M2 Ultra (64 GB)M5 Max64 GB~8Simulate output on Mac Studio M5 Max (64 GB)Orin~2Simulate output on NVIDIA Jetson AGX Orin 64GB
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to Qwen 3.5 Sql 27B Distill 2B
Qwen 3.5 family · 34 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.8 27BAlibaba | 122.0 | 17.9 GB | ~38 | same size |
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | same size |
| Gemma 3 27B ITGoogle | 79.4 | 21.7 GB | ~36 | same size |
| Gemma 2 27B ITGoogle | 72.7 | 19.5 GB | ~37 | same size |
| Gemma 4 26B A4BGoogle | — | 16.5 GB | ~171 | same size |
| Ariarhymes-ai | — | 20.2 GB | ~168 | same size |
Specifications
- Publisher
- AlioLeuchtmann
- Family
- Qwen 3.5
- Parameters
- 27B
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-08-11
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen 3.5 Sql 27B Distill 2B need?
Qwen 3.5 Sql 27B Distill 2B requires 54.4 GB of VRAM at BF16. Full 262K context adds up to 3.1 GB (57.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 27B × 16 bits ÷ 8 = 54 GB
KV Cache + Overhead ≈ 0.4 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.
KV Cache + Overhead ≈ 3.5 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Qwen 3.5 Sql 27B Distill 2B?
No — Qwen 3.5 Sql 27B Distill 2B requires at least 54.4 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Qwen 3.5 Sql 27B Distill 2B on a Mac?
Yes — Mac Pro M2 Ultra (64 GB) and 41 other Macs can run Qwen 3.5 Sql 27B Distill 2B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 54.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run Qwen 3.5 Sql 27B Distill 2B locally?
Yes — Qwen 3.5 Sql 27B Distill 2B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen 3.5 Sql 27B Distill 2B?
At BF16, Qwen 3.5 Sql 27B Distill 2B can reach ~88 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 ÷ 54.4 × 0.65 = ~96 tok/s
Estimated speed at BF16 (54.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen 3.5 Sql 27B Distill 2B?
At BF16, the download is about 54.00 GB.
Which GPUs can run Qwen 3.5 Sql 27B Distill 2B?
No single consumer GPU has enough VRAM to run Qwen 3.5 Sql 27B Distill 2B at BF16 (54.4 GB). Multi-GPU or professional hardware is required.
Which devices can run Qwen 3.5 Sql 27B Distill 2B?
52 devices with unified memory can run Qwen 3.5 Sql 27B Distill 2B at BF16 (54.4 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.