Quark 135M — Hardware Requirements & GPU Compatibility
Chat
Quark 135M is a 135M-parameter open language model from ThingAI. It supports a context window of up to 2,048 tokens. At BF16 it needs about 0.62 GB of VRAM — see which GPUs and Macs can run it below.
368 downloads
6 likesSpecifications
- Publisher
- ThingAI
- Parameters
- 135M
- Architecture
- LlamaForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2026-05-26
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Quark 135M Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 0.6 GB | — | 0.27 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Quark 135M?
BF16 · 0.6 GBQuark 135M (BF16) requires 0.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Quark 135M?
BF16 · 0.6 GB33 devices with unified memory can run Quark 135M, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Quark 135M need?
Quark 135M requires 0.6 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 135M × 16 bits ÷ 8 = 0.3 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF160.6 GB- Can I run Quark 135M on a Mac?
Quark 135M requires at least 0.6 GB at BF16, 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 Quark 135M locally?
Yes — Quark 135M can run locally on consumer hardware. At BF16 quantization it needs 0.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Quark 135M?
At BF16, Quark 135M can reach ~4702 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~1057 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 ÷ 0.6 × 0.55 = ~4702 tok/s
Estimated speed at BF16 (0.6 GB)
~4702 tok/s~1057 tok/s~3514 tok/s~2907 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Quark 135M?
At BF16, the download is about 0.27 GB.
- Which GPUs can run Quark 135M?
35 consumer GPUs can run Quark 135M at BF16 (0.6 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Quark 135M?
33 devices with unified memory can run Quark 135M at BF16 (0.6 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.