Gemma 4 31B IT Speculator.eagle3 — Hardware Requirements & GPU Compatibility
Chat
Gemma 4 31B IT Speculator.eagle3 is a 31B-parameter open language model from RedHatAI in the Gemma 4 family. At Q4_K_M it needs about 20.46 GB of VRAM — see which GPUs and Macs can run it below.
100.2K downloads
49 likesSpecifications
- Publisher
- RedHatAI
- Family
- Gemma 4
- Parameters
- 31B
- Architecture
- Eagle3DraftModel
- Release Date
- 2026-04-09
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Gemma 4 31B IT Speculator.eagle3 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 14.5 GB | — | 13.18 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 16.6 GB | — | 15.11 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 20.5 GB | — | 18.60 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 24.3 GB | — | 22.09 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 28.1 GB | — | 25.57 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 34.1 GB | — | 31.00 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 68.2 GB | — | 62.00 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 Gemma 4 31B IT Speculator.eagle3?
Q4_K_M · 20.5 GBGemma 4 31B IT Speculator.eagle3 (Q4_K_M) requires 20.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 27+ GB is recommended. 5 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Gemma 4 31B IT Speculator.eagle3?
Q4_K_M · 20.5 GB21 devices with unified memory can run Gemma 4 31B IT Speculator.eagle3, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomWhere to Download Gemma 4 31B IT Speculator.eagle3
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Gemma 4 31B IT Speculator.eagle3 need?
Gemma 4 31B IT Speculator.eagle3 requires 20.5 GB of VRAM at Q4_K_M, or 68.2 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 31B × 4.8 bits ÷ 8 = 18.6 GB
KV Cache + Overhead ≈ 1.9 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M20.5 GB- Can NVIDIA GeForce RTX 4090 run Gemma 4 31B IT Speculator.eagle3?
Yes, at Q4_K_M (20.5 GB) or lower. Higher quantizations like Q5_K_M (24.3 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Gemma 4 31B IT Speculator.eagle3?
For Gemma 4 31B IT Speculator.eagle3, Q4_K_M (20.5 GB) offers the best balance of quality and VRAM usage. Q5_K_M (24.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 14.5 GB.
VRAM requirement by quantization
Q2_K14.5 GBQ4_K_M ★20.5 GBQ5_K_M24.3 GBQ6_K28.1 GBQ8_034.1 GBBF1668.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Gemma 4 31B IT Speculator.eagle3 on a Mac?
Gemma 4 31B IT Speculator.eagle3 requires at least 14.5 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 Gemma 4 31B IT Speculator.eagle3 locally?
Yes — Gemma 4 31B IT Speculator.eagle3 can run locally on consumer hardware. At Q4_K_M quantization it needs 20.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Gemma 4 31B IT Speculator.eagle3?
At Q4_K_M, Gemma 4 31B IT Speculator.eagle3 can reach ~143 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~32 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 20.5 × 0.55 = ~143 tok/s
Estimated speed at Q4_K_M (20.5 GB)
~143 tok/s~32 tok/s~107 tok/s~88 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Gemma 4 31B IT Speculator.eagle3?
At Q4_K_M, the download is about 18.60 GB. The full-precision BF16 version is 62.00 GB. The smallest option (Q2_K) is 13.18 GB.
- Which GPUs can run Gemma 4 31B IT Speculator.eagle3?
5 consumer GPUs can run Gemma 4 31B IT Speculator.eagle3 at Q4_K_M (20.5 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Gemma 4 31B IT Speculator.eagle3?
21 devices with unified memory can run Gemma 4 31B IT Speculator.eagle3 at Q4_K_M (20.5 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.