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.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 2K)Best on 24 GB (BF16 · ~1524 tok/s · 2K)Macs from 8 GB (BF16 · ~167 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Blaze SFT
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve SurjoLabs/Blaze-SFT --max-model-len 2048vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (11 GB headroom) · BF16
- Generation speed
- ~544 tok/s
- generation speed
- Cost per 1M output tokens
- $0.036
- per 1M output tokens
How Much VRAM Does Blaze SFT Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.4 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 2K context · ~1524 tok/s |
Selected BF16
Brain floating point 160.4GBat 2K context
- Weights
- 0.1 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.6 GB free · ~1524 tok/s
≥50 tok/s needs ≥33 GB/s · RTX 5090 ~2709, RTX 3090 Ti ~1524
Which Hardware 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. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Blaze SFT, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.6 GB free · up to 2K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~1149Simulate output on RTX 3080RTX 2080 Ti~931Simulate output on RTX 2080 TiRTX 3070 Ti~920Simulate output on RTX 3070 TiM3*8 GB~167Simulate output on iMac 24" M3 (8 GB)Orin Nano~154Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~111Simulate output on iPhone 1720 GB
fits · 19.6 GB free · up to 2K ctx
1 GPU
RX 7900 XT~1116Simulate output on RX 7900 XT32–40 GB
fits · 31.6 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~2709Simulate output on RTX 5090M5 Max36 GB~749Simulate output on Mac Studio M5 Max (36 GB)M532 GB~250Simulate output on MacBook Air 13" M5 (32 GB)Orin~310Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~204Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Specifications
- Publisher
- SurjoLabs
- Parameters
- 48M
- Architecture
- BlazeForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 8,192
- Release Date
- 2026-09-01
- License
- MIT
Frequently 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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can I run Blaze SFT on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Blaze SFT. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 0.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run Blaze SFT locally?
Yes — Blaze SFT can run locally on consumer hardware. 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 ÷ 0.43 × 0.65 = ~12093 tok/s
Estimated speed at BF16 (0.4 GB)
Real-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?
52 consumer GPUs can run Blaze SFT 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 Blaze SFT?
163 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, 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.