Deeplm 108M — Hardware Requirements & GPU Compatibility
Chat
Deeplm 108M is a 108M-parameter open language model from samcheng0. At BF16 it needs about 0.24 GB of VRAM — see which GPUs and Macs can run it below.
4.3K downloads
5 likesSpecifications
- Publisher
- samcheng0
- Parameters
- 108M
- Release Date
- 2026-06-06
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Deeplm 108M Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 0.2 GB | — | 0.22 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 Deeplm 108M?
BF16 · 0.2 GBDeeplm 108M (BF16) requires 0.2 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 Deeplm 108M?
BF16 · 0.2 GB59 devices with unified memory can run Deeplm 108M, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomFrequently Asked Questions
- How much VRAM does Deeplm 108M need?
Deeplm 108M requires 0.2 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 108M × 16 bits ÷ 8 = 0.2 GB
VRAM usage by quantization
BF160.2 GB- Can I run Deeplm 108M on a Mac?
Deeplm 108M requires at least 0.2 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 Deeplm 108M locally?
Yes — Deeplm 108M can run locally on consumer hardware. At BF16 quantization it needs 0.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Deeplm 108M?
At BF16, Deeplm 108M can reach ~18333 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~2730 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 ÷ 0.2 × 0.65 = ~21667 tok/s
Estimated speed at BF16 (0.2 GB)
~21667 tok/s~2730 tok/s~21667 tok/s~18333 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Deeplm 108M?
At BF16, the download is about 0.22 GB.
- Which GPUs can run Deeplm 108M?
50 consumer GPUs can run Deeplm 108M at BF16 (0.2 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 Deeplm 108M?
59 devices with unified memory can run Deeplm 108M at BF16 (0.2 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.