Speck1 140M Instruct — Hardware Requirements & GPU Compatibility
Chat
Speck1 140M Instruct is a 141M-parameter open language model from specklabs. It supports a context window of up to 4,096 tokens. At BF16 it needs about 0.61 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 4K)Best on 24 GB (BF16 · ~1074 tok/s · 4K)Macs from 8 GB (BF16 · ~118 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Speck1 140M Instruct
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve specklabs/Speck1-140M-Instruct --max-model-len 4096vLLM 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
- ~384 tok/s
- generation speed
- Cost per 1M output tokens
- $0.050
- per 1M output tokens
How Much VRAM Does Speck1 140M Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.6 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 4K context · ~1074 tok/s |
Selected BF16
Brain floating point 160.6GBat 4K context
- Weights
- 0.3 GB
- KV cache
- 0.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.4 GB free · ~1074 tok/s
≥50 tok/s needs ≥47 GB/s · RTX 5090 ~1910, RTX 3090 Ti ~1074
Which Hardware Can Run Speck1 140M Instruct?
BF16 · 0.6 GBSpeck1 140M Instruct (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. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Speck1 140M Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.4 GB free · up to 4K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~810Simulate output on RTX 3080RTX 2080 Ti~656Simulate output on RTX 2080 TiRTX 3070 Ti~648Simulate output on RTX 3070 TiM3*8 GB~118Simulate output on iMac 24" M3 (8 GB)Orin Nano~109Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~78Simulate output on iPhone 1720 GB
fits · 19.4 GB free · up to 4K ctx
1 GPU
RX 7900 XT~787Simulate output on RX 7900 XT32–40 GB
fits · 31.4 GB free · up to 4K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~1910Simulate output on RTX 5090M5 Max36 GB~528Simulate output on Mac Studio M5 Max (36 GB)M532 GB~176Simulate output on MacBook Air 13" M5 (32 GB)Orin~218Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~144Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
1| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| SmolLM 135M Instruct FP32modularai | — | 0.4 GB | ~1524 | same size |
Specifications
- Publisher
- specklabs
- Parameters
- 141M
- Architecture
- SpeckForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 32,003
- Release Date
- 2026-08-24
- License
- MIT
Frequently Asked Questions
How much VRAM does Speck1 140M Instruct need?
Speck1 140M Instruct requires 0.6 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 141M × 16 bits ÷ 8 = 0.3 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 ≈ 0.3 GB (at full 4K context)
VRAM usage by quantization
Can I run Speck1 140M Instruct on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Speck1 140M Instruct. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 0.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Speck1 140M Instruct locally?
Yes — Speck1 140M Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Speck1 140M Instruct?
At BF16, Speck1 140M Instruct can reach ~7869 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1074 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 ÷ 0.61 × 0.65 = ~8525 tok/s
Estimated speed at BF16 (0.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Speck1 140M Instruct?
At BF16, the download is about 0.28 GB.
Which GPUs can run Speck1 140M Instruct?
52 consumer GPUs can run Speck1 140M Instruct 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 Speck1 140M Instruct?
163 devices with unified memory can run Speck1 140M Instruct at BF16 (0.6 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.