G9v3-39A5B
ai9starsapache-2.0text

G9v3-39A5B

Updated Aug 10, 2026
Parameters
39B
Context
131,072
License
apache-2.0
Updated
Aug 10, 2026

Intelligence benchmarks

Artificial Analysis indexes - compared with the best open and proprietary models

Intelligence

31.4

AA Index

Agentic

28.7

AA Index

Intelligence Index - G9v3-39A5B vs. the field

Best open-weight models (you can run locally) and leading proprietary models for context.

Claude Opus 5 (max)
63.1
closed
Claude Fable 5 (with fallback)
62.1
closed
GPT-5.6 Sol (max)
60.9
closed
Kimi K3
59.7
open
Qwen3.8 Max
58.1
closed
Muse Spark 1.2 (xhigh)
56.8
closed
GLM-5.2
52.6
open
G9v3-39A5B
31.4
open

Agentic Index comparison

Claude Opus 5 (max)
59.2
closed
Qwen3.8 Max
58.4
closed
GPT-5.6 Sol (max)
57.8
closed
Claude Fable 5 (with fallback)
56.6
closed
Kimi K3
54.3
open
GPT-5.6 Terra (max)
50.2
closed
DeepSeek V4 Flash 0731
48.4
open
G9v3-39A5B
28.7
open

Benchmark data from Artificial Analysis · updated 2026-08-10.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GPQA75.6

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Too big for 24 GB at any quant
0 of 4 quantizations fit G9v3-39A5B with real runtime overhead.

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve ai9stars/G9v3-39A5B

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

G9v3-39A5B is a 39B-parameter apache-2.0 model from AI9Stars. It scores 30.9 on the Artificial Analysis Intelligence Index. At Q4_K_M it needs roughly 23 GB of VRAM, placing it in the 12–24 GB GPU hardware tier.

Benchmarks

Artificial Analysis Intelligence Index - G9v3-39A5B vs. leading closed models:

ModelIntelligenceCodingGPQA
G9v3-39A5B30.9-75.6
Claude Opus 5 (max)60.7-93.2
Claude Fable 5 (with fallback)59.9-92.6
GPT-5.6 Sol (max)58.9-94.1
GPT-5.6 Terra (max)55-92.5
Muse Spark 1.2 (xhigh)54.1-90.4

Source: Artificial Analysis (2026-08-06).

Popularity

G9v3-39A5B has 37 downloads in the last month on HuggingFace and 43 likes.

Frequently asked

Quick answers to common questions

How much VRAM does G9v3-39A5B need?

G9v3-39A5B with 39B parameters needs approximately 23 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is G9v3-39A5B better than other ai9stars models?

G9v3-39A5B has 39B parameters with 131,072 context - a strong choice for general use.

What license is G9v3-39A5B under?

G9v3-39A5B is released under the apache-2.0 license, making it suitable for most commercial and personal projects.

What hardware runs G9v3-39A5B well?

With 39B parameters, G9v3-39A5B requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for G9v3-39A5B?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~28 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can G9v3-39A5B's context window handle?

G9v3-39A5B supports a 131,072-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with G9v3-39A5B?

G9v3-39A5B competes with other 20B–59B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec

Comments coming soon

Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.