G9v3 39A5B — Hardware Requirements & GPU Compatibility
Chat
G9v3 39A5B is a 39.0B-parameter open language model from ai9stars. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 23.72 GB of VRAM — see which GPUs and Macs can run it below.
4.7K downloads
93 likesSpecifications
- Publisher
- ai9stars
- Parameters
- 39.0B
- Architecture
- G9v3ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 130,560
- Release Date
- 2026-07-21
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does G9v3 39A5B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 16.9 GB | 19.4 GB | 16.56 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 19.3 GB | 21.9 GB | 19.00 GB | 3-bit medium quantization |
| IQ4_XS | 4.30 | 21.3 GB | 23.8 GB | 20.95 GB | Importance-weighted 4-bit, compact |
| Q4_K_M | 4.80 | 23.7 GB | 26.2 GB | 23.38 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 28.1 GB | 30.6 GB | 27.76 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 32.5 GB | 35 GB | 32.15 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 39.3 GB | 41.8 GB | 38.97 GB | 8-bit quantization, near-lossless |
| BF16 | 16.00 | 78.3 GB | 80.8 GB | 77.93 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 G9v3 39A5B?
Q4_K_M · 23.7 GBG9v3 39A5B (Q4_K_M) requires 23.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 31+ GB is recommended. Using the full 131K context window can add up to 2.5 GB, bringing total usage to 26.2 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Which Devices Can Run G9v3 39A5B?
Q4_K_M · 23.7 GB41 devices with unified memory can run G9v3 39A5B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download G9v3 39A5B
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 G9v3 39A5B need?
G9v3 39A5B requires 23.7 GB of VRAM at Q4_K_M, or 78.3 GB at BF16. Full 131K context adds up to 2.5 GB (26.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 39.0B × 4.8 bits ÷ 8 = 23.4 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 2.8 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M23.7 GBQ4_K_M + full context26.2 GB- Can NVIDIA GeForce RTX 4090 run G9v3 39A5B?
Yes, at Q4_K_M (23.7 GB) or lower. Higher quantizations like Q5_K_M (28.1 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for G9v3 39A5B?
For G9v3 39A5B, Q4_K_M (23.7 GB) offers the best balance of quality and VRAM usage. Q5_K_M (28.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 16.9 GB.
VRAM requirement by quantization
Q2_K16.9 GBIQ4_XS21.3 GBQ4_K_M ★23.7 GBQ5_K_M28.1 GBQ6_K32.5 GBBF1678.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run G9v3 39A5B on a Mac?
G9v3 39A5B requires at least 16.9 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 G9v3 39A5B locally?
Yes — G9v3 39A5B can run locally on consumer hardware. At Q4_K_M quantization it needs 23.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is G9v3 39A5B?
At Q4_K_M, G9v3 39A5B can reach ~202 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~28 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 ÷ 23.7 × 0.65 = ~219 tok/s
Estimated speed at Q4_K_M (23.7 GB)
~219 tok/s~28 tok/s~219 tok/s~202 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of G9v3 39A5B?
At Q4_K_M, the download is about 23.38 GB. The full-precision BF16 version is 77.93 GB. The smallest option (Q2_K) is 16.56 GB.
- Which GPUs can run G9v3 39A5B?
7 consumer GPUs can run G9v3 39A5B at Q4_K_M (23.7 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run G9v3 39A5B?
41 devices with unified memory can run G9v3 39A5B at Q4_K_M (23.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.