Pantheon Reasoning 31B 1.1 — Hardware Requirements & GPU Compatibility
ChatRoleplayReasoning
Pantheon Reasoning 31B 1.1 is a 32.7B-parameter open language model from Gryphe. It supports a context window of up to 262,144 tokens. At BF16 it needs about 66.99 GB of VRAM — see which GPUs and Macs can run it below.
Pantheon Reasoning 31B 1.1 runs on a 96 GB+ Mac or a workstation GPU
Best local pick → Mac Studio (M3 Ultra, 96GB) · BF16 · 68.3 GB · ~9 tok/s
Macs from 96 GB (BF16 · ~9 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Pantheon Reasoning 31B 1.1
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve Gryphe/Pantheon-Reasoning-31B-1.1 --max-model-len 16384 --tensor-parallel-size 8vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX PRO 6000 (96 GB) (27 GB headroom) · BF16
- Generation speed
- ~17 tok/s
- generation speed
- Cost per 1M output tokens
- $21.38
- per 1M output tokens
How Much VRAM Does Pantheon Reasoning 31B 1.1 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 67.0 GB | 70.4 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on RTX PRO 5000 Blackwell 72 GB |
Selected BF16
Brain floating point 1668.3GBat 16K context
- Weights
- 65.4 GB
- KV cache
- 2.6 GB
- Overhead
- 0.3 GB
Server-class: ~68.3 GB at 16K context · one RTX PRO 5000 Blackwell 72 GB
Which Hardware Can Run Pantheon Reasoning 31B 1.1?
BF16 · 67.0 GBPantheon Reasoning 31B 1.1 (BF16) requires 67.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 88+ GB is recommended. Using the full 262K context window can add up to 33.0 GB, bringing total usage to 100.0 GB. No consumer GPU has enough memory. 30 devices with unified memory can run Pantheon Reasoning 31B 1.1, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 96GB).
96 GB
fits · 27.7 GB free · up to 128K ctx
3 GPUs · 2 Mac classes
RTX PRO 6000 Blackwell Max-Q Workstation Edition~17Simulate output on RTX PRO 6000 Blackwell Max-Q Workstation EditionRTX PRO 6000 Blackwell Workstation Edition~17Simulate output on RTX PRO 6000 Blackwell Workstation EditionRTX PRO 6000 Blackwell Server Edition~16Simulate output on RTX PRO 6000 Blackwell Server EditionM3 Ultra*96 GB~9Simulate output on Mac Studio (M3 Ultra, 96GB)M3 Max*96 GB~3Simulate output on MacBook Pro 14" M3 Max (96 GB)128–144 GB
fits · 59.7 GB free · up to 256K ctx
4 GPUs · 2 Mac classes · 4 device families
GH200 Grace Hopper Superchip~48Simulate output on GH200 Grace Hopper SuperchipH200 NVL~47Simulate output on H200 NVLH200 SXM~47Simulate output on H200 SXMM2 Ultra*128 GB~8Simulate output on Mac Pro M2 Ultra (128 GB)M5 Max128 GB~6Simulate output on Mac Studio M5 Max (128 GB)GB10~3Simulate output on ASUS Ascent GX10Jetson T5000 (Thor)~3Simulate output on NVIDIA Jetson AGX Thor Developer Kit
By VRAM tier · typical GPUs and Macs at BF16
Consumer GPUs (up to 32 GB) and Macs up to 64 GB: too small for this model (needs ≥ 68.3 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.7 35B A3BOpenBMB | — | 22.1 GB | ~169 | same size |
| NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA | — | 19.3 GB | ~197 | same size |
| Agents A1InternScience | — | 21.5 GB | ~171 | same size |
| Ornith 1.0 35BDeep Reinforce | — | 21.5 GB | ~171 | same size |
| EXAONE 4.5 33BLGAI-EXAONE | — | 23.9 GB | ~33 | same size |
| Gemma 4 31BGoogle | — | 22.6 GB | ~31 | same size |
Specifications
- Publisher
- Gryphe
- Parameters
- 32.7B
- Architecture
- Gemma4ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-06-18
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Pantheon Reasoning 31B 1.1 need?
Pantheon Reasoning 31B 1.1 requires 67.0 GB of VRAM at BF16. Full 262K context adds up to 33.0 GB (100.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32.7B × 16 bits ÷ 8 = 65.4 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 5090 run Pantheon Reasoning 31B 1.1?
No — Pantheon Reasoning 31B 1.1 requires at least 67.0 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Pantheon Reasoning 31B 1.1 on a Mac?
Yes — Mac Studio (M3 Ultra, 96GB) and 20 other Macs can run Pantheon Reasoning 31B 1.1. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 67.0 GB of usable unified memory (RAM minus macOS overhead).
Can I run Pantheon Reasoning 31B 1.1 locally?
Yes — Pantheon Reasoning 31B 1.1 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Pantheon Reasoning 31B 1.1?
At BF16, Pantheon Reasoning 31B 1.1 can reach ~72 tok/s on AMD Instinct MI350X. 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 ÷ 67.0 × 0.65 = ~78 tok/s
Estimated speed at BF16 (67.0 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Pantheon Reasoning 31B 1.1?
At BF16, the download is about 65.36 GB.
Which GPUs can run Pantheon Reasoning 31B 1.1?
No single consumer GPU has enough VRAM to run Pantheon Reasoning 31B 1.1 at BF16 (67.0 GB). Multi-GPU or professional hardware is required.
Which devices can run Pantheon Reasoning 31B 1.1?
30 devices with unified memory can run Pantheon Reasoning 31B 1.1 at BF16 (67.0 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (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.