Quasar 10B — Hardware Requirements & GPU Compatibility
Chat
Quasar 10B is a 8.6B-parameter open language model from silx-ai. It supports a context window of up to 2,097,152 tokens. At BF16 it needs about 17.77 GB of VRAM — see which GPUs and Macs can run it below.
4.9K downloads
49 likesSpecifications
- Publisher
- silx-ai
- Parameters
- 8.6B
- Architecture
- QuasarForCausalLM
- Context Length
- 2,097,152 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-03-09
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Quasar 10B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 17.8 GB | 292.4 GB | 17.20 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Quasar 10B?
BF16 · 17.8 GBQuasar 10B (BF16) requires 17.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 24+ GB is recommended. Using the full 2097K context window can add up to 274.6 GB, bringing total usage to 292.4 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 Quasar 10B?
BF16 · 17.8 GB21 devices with unified memory can run Quasar 10B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomFrequently Asked Questions
- How much VRAM does Quasar 10B need?
Quasar 10B requires 17.8 GB of VRAM at BF16. Full 2097K context adds up to 274.6 GB (292.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.6B × 16 bits ÷ 8 = 17.2 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 275.2 GB (at full 2097K context)
VRAM usage by quantization
BF1617.8 GBBF16 + full context292.4 GB- Can I run Quasar 10B on a Mac?
Quasar 10B requires at least 17.8 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 Quasar 10B locally?
Yes — Quasar 10B can run locally on consumer hardware. At BF16 quantization it needs 17.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Quasar 10B?
At BF16, Quasar 10B can reach ~164 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~37 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 ÷ 17.8 × 0.55 = ~164 tok/s
Estimated speed at BF16 (17.8 GB)
~164 tok/s~37 tok/s~123 tok/s~101 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Quasar 10B?
At BF16, the download is about 17.20 GB.
- Which GPUs can run Quasar 10B?
6 consumer GPUs can run Quasar 10B at BF16 (17.8 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 Quasar 10B?
21 devices with unified memory can run Quasar 10B at BF16 (17.8 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.