Blaze SFT — Hardware Requirements & GPU Compatibility
Chat
Blaze SFT is a 48M-parameter open language model from SurjoLabs. It supports a context window of up to 2,048 tokens. At BF16 it needs about 0.43 GB of VRAM — see which GPUs and Macs can run it below.
1.3K downloads
2 likesSpecifications
- Publisher
- SurjoLabs
- Parameters
- 48M
- Architecture
- BlazeForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 8,192
- Release Date
- 2026-09-01
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Blaze SFT Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 0.4 GB | — | 0.10 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 Blaze SFT?
BF16 · 0.4 GBBlaze SFT (BF16) requires 0.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Blaze SFT?
BF16 · 0.4 GB59 devices with unified memory can run Blaze SFT, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomFrequently Asked Questions
- How much VRAM does Blaze SFT need?
Blaze SFT requires 0.4 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 48M × 16 bits ÷ 8 = 0.1 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF160.4 GB- Can I run Blaze SFT on a Mac?
Blaze SFT requires at least 0.4 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 Blaze SFT locally?
Yes — Blaze SFT can run locally on consumer hardware. At BF16 quantization it needs 0.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Blaze SFT?
At BF16, Blaze SFT can reach ~11163 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1524 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 ÷ 0.4 × 0.65 = ~12093 tok/s
Estimated speed at BF16 (0.4 GB)
~12093 tok/s~1524 tok/s~12093 tok/s~11163 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Blaze SFT?
At BF16, the download is about 0.10 GB.
- Which GPUs can run Blaze SFT?
50 consumer GPUs can run Blaze SFT at BF16 (0.4 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 50 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Blaze SFT?
59 devices with unified memory can run Blaze SFT at BF16 (0.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.