Model
Model explorer

StableLM-Alpha 7B

OPEN
Stability AI · StableLM family · released Apr 19, 2023

Stability AI's debut open-weights suite (3B/7B alpha), part of the early post-LLaMA open-model wave; later superseded.

ReasoningCodingVisionFunction callingTool useAgentic
-552.2
Elo · rank #450
Parameters
7B
Active params
7B (dense)
Context
4K tokens
Architecture
Dense decoder-only transformer (GPT-NeoX style, parallel attention+FFN)
License
CC BY-SA-4.0
Languages
1+
API price (in/out)
No hosted API
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
ARC-ChallengeReasoning32.0%#160
best: Llama 3.1 405B · 96.9%
GSM8KMath0.0%#201
best: Llama 3.1 405B · 96.8%
HellaSwagReasoning51.8%#149
best: Claude 3 Opus · 95.4%
MMLUKnowledge26.2%#283
best: OpenAI o3 · 92.9%
TruthfulQAKnowledge40.2%#80
best: Phi-3.5-MoE (16x3.8B, 6.6B active) · 77.5%
WinoGrandeReasoning55.4%#136
best: PaLM 2 · 90.9%
Run it locally
VRAM @ Q4
4.5 GB
VRAM @ FP16
14 GB
Fits on (Q4)
RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB
Throughput data unavailable.
Quantizations
GGUF
StableLM family
Elo progression across releases
StableLM-Alpha 7BApr 2023-552.2StableLM-3B-4e1tOct 2023-203.6StableLM Zephyr 3BDec 2023-0.4
Resources
HFstabilityai/stablelm-base-alpha-7bGHStability-AI/StableLM
API price weights · each benchmark row carries its own source badge (see methodology)