Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/graycodeai/starling/research-bitsandbytesnpx skills add GrayCodeAI/starling --skill research-bitsandbytesgit clone --depth 1 https://github.com/GrayCodeAI/starlingWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00060 | $0.02858 |
| Opus 5 | $0.00030 | $0.01429 |
| Sonnet 5 | $0.00012 | $0.00572 |
| Haiku 4.5 | $0.00006 | $0.00286 |
Grade A, and why
research-bitsandbytes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
88% identical to quantizing-models-bitsandbytes — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bitsandbytes - LLM Quantization
Quick start
bitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with <1% accuracy loss.
Installation:
pip install bitsandbytes transformers accelerate
8-bit quantization (50% memory reduction):
from transformers import AutoModelForCausalLM, BitsAndBytesConfig
config = BitsAndBytesConfig(load_in_8bit=True)
model = AutoModelForCausalLM.from_pretrained(
"meta-llama/Llama-2-7b-hf",
quantization_config=config,
device_map="auto"
)
# Memory: 14GB → 7GB
4-bit quantization (75% memory reduction):
config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.float16
)
model = AutoModelForCausalLM.from_pretrained(
"meta-llama/Llama-2-7b-hf",
quantization_config=config,
device_map="auto"
)
# Memory: 14GB → 3.5GB
Common workflows
Workflow 1: Load large model in limited GPU memory
Copy this checklist:
Quantization Loading:
- [ ] Step 1: Calculate memory requirements
- [ ] Step 2: Choose quantization level (4-bit or 8-bit)
- [ ] Step 3: Configure quantization
- [ ] Step 4: Load and verify model
Step 1: Calculate memory requirements
Estimate model memory:
FP16 memory (GB) = Parameters × 2 bytes / 1e9
INT8 memory (GB) = Parameters × 1 byte / 1e9
INT4 memory (GB) = Parameters × 0.5 bytes / 1e9
Example (Llama 2 7B):
FP16: 7B × 2 / 1e9 = 14 GB
INT8: 7B × 1 / 1e9 = 7 GB
INT4: 7B × 0.5 / 1e9 = 3.5 GB
Step 2: Choose quantization level
| GPU VRAM | Model Size | Recommended |
|---|---|---|
| 8 GB | 3B | 4-bit |
| 12 GB | 7B | 4-bit |
| 16 GB | 7B | 8-bit or 4-bit |
| 24 GB | 13B | 8-bit or 70B 4-bit |
| 40+ GB | 70B | 8-bit |
Step 3: Configure quantization
For 8-bit (better accuracy):
from transformers import BitsAndBytesConfig
import torch
config = BitsAndBytesConfig(
load_in_8bit=True,
llm_int8_threshold=6.0, # Outlier threshold
llm_int8_has_fp16_weight=False
)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 408 lines · 60 tokens per session scan A da58b1c369da
research-bitsandbytes is a skill published in the GitHub repository GrayCodeAI/starling (2 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 2,858 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to quantizing-models-bitsandbytes, differing in 18 lines, and is treated as a copy.
Other skills, from other repositories
quantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
quantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
quantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
awq-quantization
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper…
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.