Pebble 10M Chat — Hardware Requirements & GPU Compatibility
Chat
Pebble 10M Chat is a 11M-parameter open language model from basically-ai. It supports a context window of up to 512 tokens. At Q4_K_M it needs about 0.01 GB of VRAM — see which GPUs and Macs can run it below.
1.2K downloads
13 likesSpecifications
- Publisher
- basically-ai
- Parameters
- 11M
- Architecture
- Pebble10MLM
- Context Length
- 512 tokens
- Vocabulary Size
- 2,048
- Release Date
- 2026-08-31
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Pebble 10M Chat Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 0.0 GB | — | 0.01 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 0.0 GB | — | 0.01 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 0.0 GB | — | 0.01 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 0.0 GB | — | 0.01 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 0.0 GB | — | 0.01 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 0.0 GB | — | 0.01 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 0.0 GB | — | 0.02 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 Pebble 10M Chat?
Q4_K_M · 0.0 GBPebble 10M Chat (Q4_K_M) requires 0.0 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 Pebble 10M Chat?
Q4_K_M · 0.0 GB59 devices with unified memory can run Pebble 10M Chat, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download Pebble 10M Chat
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Frequently Asked Questions
- How much VRAM does Pebble 10M Chat need?
Pebble 10M Chat requires 0.0 GB of VRAM at Q4_K_M, or 0.0 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 11M × 4.8 bits ÷ 8 = 0 GB
VRAM usage by quantization
Q4_K_M0.0 GB- What's the best quantization for Pebble 10M Chat?
For Pebble 10M Chat, Q4_K_M (0.0 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.0 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.0 GB.
VRAM requirement by quantization
Q2_K0.0 GBQ4_K_M ★0.0 GBQ5_K_M0.0 GBQ6_K0.0 GBQ8_00.0 GBBF160.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Pebble 10M Chat on a Mac?
Pebble 10M Chat requires at least 0.0 GB at Q2_K, 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 Pebble 10M Chat locally?
Yes — Pebble 10M Chat can run locally on consumer hardware. At Q4_K_M quantization it needs 0.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Pebble 10M Chat?
At Q4_K_M, Pebble 10M Chat can reach ~480000 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~65520 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 ÷ 0.0 × 0.65 = ~520000 tok/s
Estimated speed at Q4_K_M (0.0 GB)
~520000 tok/s~65520 tok/s~520000 tok/s~480000 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Pebble 10M Chat?
At Q4_K_M, the download is about 0.01 GB. The full-precision BF16 version is 0.02 GB. The smallest option (Q2_K) is 0.01 GB.
- Which GPUs can run Pebble 10M Chat?
50 consumer GPUs can run Pebble 10M Chat at Q4_K_M (0.0 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 Pebble 10M Chat?
59 devices with unified memory can run Pebble 10M Chat at Q4_K_M (0.0 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.