SpatialLM1.1 Qwen 0.5B — Hardware Requirements & GPU Compatibility
Chat
SpatialLM1.1 Qwen 0.5B is a 604M-parameter open language model from manycore-research in the Qwen family. It supports a context window of up to 32,768 tokens. At BF16 it needs about 1.53 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 32K)Best on 24 GB (BF16 · ~428 tok/s · 32K)Macs from 8 GB (BF16 · ~47 tok/s)
CC BY-NC 4.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run SpatialLM1.1 Qwen 0.5B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve manycore-research/SpatialLM1.1-Qwen-0.5B --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 3060 12GB (10 GB headroom) · BF16
- Generation speed
- ~153 tok/s
- generation speed
- Cost per 1M output tokens
- $0.15
- per 1M output tokens
How Much VRAM Does SpatialLM1.1 Qwen 0.5B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.5 GB | 1.9 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~428 tok/s |
Selected BF16
Brain floating point 161.7GBat 16K context
- Weights
- 1.2 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.3 GB free · ~428 tok/s
≥50 tok/s needs ≥118 GB/s · RTX 5090 ~761, RTX 3090 Ti ~428
Which Hardware Can Run SpatialLM1.1 Qwen 0.5B?
BF16 · 1.5 GBSpatialLM1.1 Qwen 0.5B (BF16) requires 1.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 33K context window can add up to 0.4 GB, bringing total usage to 1.9 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run SpatialLM1.1 Qwen 0.5B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.3 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~323Simulate output on RTX 3080RTX 2080 Ti~262Simulate output on RTX 2080 TiRTX 3070 Ti~258Simulate output on RTX 3070 TiM3*8 GB~47Simulate output on iMac 24" M3 (8 GB)Orin Nano~43Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~31Simulate output on iPhone 1720 GB
fits · 18.3 GB free · up to 32K ctx
1 GPU
RX 7900 XT~314Simulate output on RX 7900 XT32–40 GB
fits · 30.3 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~761Simulate output on RTX 5090M5 Max36 GB~211Simulate output on Mac Studio M5 Max (36 GB)M532 GB~70Simulate output on MacBook Air 13" M5 (32 GB)Orin~87Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~57Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to SpatialLM1.1 Qwen 0.5B
Qwen family · 28 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| D1 Omni 600MLiquid AI | — | 1.2 GB | ~910 | same size |
| T5gemma B B Ul2 ITGoogle | — | 2.5 GB | ~504 | same size |
| Qwen3 0.6B BaseAlibaba | — | 1.6 GB | ~840 | same size |
| Bloomz 560MBigScience | — | 0.4 GB | ~1771 | same size |
| Bloom 560MBigScience | — | 1.6 GB | ~1771 | same size |
| Xglm 564MMeta | — | 0.4 GB | ~1771 | same size |
Specifications
- Publisher
- manycore-research
- Family
- Qwen
- Parameters
- 604M
- Architecture
- SpatialLMQwenForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-06-06
- License
- CC BY-NC 4.0
Frequently Asked Questions
How much VRAM does SpatialLM1.1 Qwen 0.5B need?
SpatialLM1.1 Qwen 0.5B requires 1.5 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 604M × 16 bits ÷ 8 = 1.2 GB
KV Cache + Overhead ≈ 0.3 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 ≈ 0.7 GB (at full 33K context)
VRAM usage by quantization
Can I run SpatialLM1.1 Qwen 0.5B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run SpatialLM1.1 Qwen 0.5B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 1.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run SpatialLM1.1 Qwen 0.5B locally?
Yes — SpatialLM1.1 Qwen 0.5B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is SpatialLM1.1 Qwen 0.5B?
At BF16, SpatialLM1.1 Qwen 0.5B can reach ~3137 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~428 tok/s. 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 ÷ 1.53 × 0.65 = ~3399 tok/s
Estimated speed at BF16 (1.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of SpatialLM1.1 Qwen 0.5B?
At BF16, the download is about 1.21 GB.
Which GPUs can run SpatialLM1.1 Qwen 0.5B?
52 consumer GPUs can run SpatialLM1.1 Qwen 0.5B at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run SpatialLM1.1 Qwen 0.5B?
163 devices with unified memory can run SpatialLM1.1 Qwen 0.5B at BF16 (1.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.