Gemma 4 31B IT Heretic — Hardware Requirements & GPU Compatibility
VisionCode
Gemma 4 31B IT Heretic is a 31.3B-parameter open language model from coder3101 in the Gemma 4 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 20.39 GB of VRAM — see which GPUs and Macs can run it below.
Decent on a 24 GB GPU
Runs from 12 GB (IQ2_XXS · 16K)Best on 24 GB (Q4_K_M · ~32 tok/s · 32K)Macs from 16 GB (IQ2_XS · ~13 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma 4 31B IT Heretic
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/mradermacher/gemma-4-31B-it-heretic-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 2.3 GB free · 16K context
Download: gemma-4-31B-it-heretic.Q4_K_M.gguf18.69 GBmradermacher
Other ways
each opens step-by-stepRun in cloud
Fits on RTX A6000 (48 GB) (26 GB headroom) · Q4_K_M
- Generation speed
- ~25 tok/s
- generation speed
- Cost per 1M output tokens
- $3.74
- per 1M output tokens
How Much VRAM Does Gemma 4 31B IT Heretic Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 14.9 GB | 18.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 64K context · ~44 tok/s | |
| 15.3 GB | 18.7 GB | 3-bit small — 3-bit small quantization | Fits: 64K context · ~43 tok/s | |
| 16.9 GB | 20.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~39 tok/s | |
| 17.3 GB | 20.7 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~38 tok/s | |
| 20.4 GB | 23.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~32 tok/s | |
| 23.9 GB | 27.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 4K context · ~27 tok/s | |
| 27.4 GB | 30.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 28.7 GB | |
| 32.9 GB | 36.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 34.2 GB |
Selected Q4_K_M
4-bit medium quantization21.7GBat 16K context
- Weights
- 18.8 GB
- KV cache
- 2.6 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 2.3 GB free · ~32 tok/s
≥50 tok/s needs ≥1.57 TB/s · RTX 5090 ~57
Which Hardware Can Run Gemma 4 31B IT Heretic?
Q4_K_M · 20.4 GBGemma 4 31B IT Heretic (Q4_K_M) requires 20.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 27+ GB is recommended. Using the full 262K context window can add up to 33.0 GB, bringing total usage to 53.4 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Gemma 4 31B IT Heretic, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit IQ4_XS (19.8 GB)
1 GPU
RX 7900 XT~26Simulate output on RX 7900 XT32–40 GB
fits · 10.3 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~57Simulate output on RTX 5090M5 Max36 GB~16Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Gemma 4 31B IT Heretic
Gemma 4 family · 35 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Hy Memory 30B A3BTencent | — | 19.1 GB | ~184 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Llm Jp 4.1 33B Thinkingllm-jp | — | 22.5 GB | ~35 | same size |
| Agnes 3.0 FlashAgnes-AI | — | 22.1 GB | ~35 | same size |
| Muse Glimmer 30BMeta | — | 19.6 GB | ~36 | same size |
| NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA | — | 19.3 GB | ~197 | same size |
Specifications
- Publisher
- coder3101
- Family
- Gemma 4
- Parameters
- 31.3B
- Architecture
- Gemma4ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-04-02
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Gemma 4 31B IT Heretic need?
Gemma 4 31B IT Heretic requires 20.4 GB of VRAM at Q4_K_M, or 64.2 GB at BF16. Full 262K context adds up to 33.0 GB (53.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 31.3B × 4.8 bits ÷ 8 = 18.8 GB
KV Cache + Overhead ≈ 1.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 34.6 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Gemma 4 31B IT Heretic?
Yes, at Q5_K_M (23.9 GB) or lower. Higher quantizations like Q6_K (27.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Gemma 4 31B IT Heretic?
For Gemma 4 31B IT Heretic, Q4_K_M (20.4 GB) offers the best balance of quality and VRAM usage. Q5_K_S (23.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 10.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 4 31B IT Heretic on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Gemma 4 31B IT Heretic, the smallest at IQ2_XS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 20.4 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Gemma 4 31B IT Heretic locally?
Yes — Gemma 4 31B IT Heretic can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 4 31B IT Heretic?
At Q4_K_M, Gemma 4 31B IT Heretic can reach ~235 tok/s on AMD Instinct MI350X. 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: NVIDIA B200 → 8000 ÷ 20.4 × 0.65 = ~255 tok/s
Estimated speed at Q4_K_M (20.4 GB)
Real-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 Heretic?
At Q4_K_M, the download is about 18.76 GB. The full-precision BF16 version is 62.55 GB. The smallest option (IQ2_XXS) is 8.60 GB.
Which GPUs can run Gemma 4 31B IT Heretic?
7 consumer GPUs can run Gemma 4 31B IT Heretic at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Gemma 4 31B IT Heretic?
122 devices with unified memory can run Gemma 4 31B IT Heretic at Q4_K_M (20.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.