Pantheon Reasoning 26B A4B 1.1 v2 — Hardware Requirements & GPU Compatibility
ChatRoleplayReasoning
Pantheon Reasoning 26B A4B 1.1 v2 is a 26.5B-parameter open language model from Gryphe. It supports a context window of up to 262,144 tokens. At BF16 it needs about 53.73 GB of VRAM — see which GPUs and Macs can run it below.
Pantheon Reasoning 26B A4B 1.1 v2 runs on a 64 GB+ Mac or a workstation GPU
Best local pick → Mac Pro M2 Ultra (64 GB) · BF16 · 54.1 GB · ~41 tok/s
Macs from 64 GB (BF16 · ~41 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Pantheon Reasoning 26B A4B 1.1 v2
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve Gryphe/Pantheon-Reasoning-26B-A4B-1.1-V2 --max-model-len 16384vLLM 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) (41 GB headroom) · BF16
- Generation speed
- ~95 tok/s
- generation speed
- Cost per 1M output tokens
- $3.93
- per 1M output tokens
How Much VRAM Does Pantheon Reasoning 26B A4B 1.1 v2 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 53.7 GB | 54.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 54.1 GB |
Selected BF16
Brain floating point 1654.1GBat 16K context
- Weights
- 53.1 GB
- KV cache
- 0.7 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 30.1 GB more
Which Hardware Can Run Pantheon Reasoning 26B A4B 1.1 v2?
BF16 · 53.7 GBPantheon Reasoning 26B A4B 1.1 v2 (BF16) requires 53.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 70+ GB is recommended. Using the full 262K context window can add up to 8.7 GB, bringing total usage to 62.4 GB. No consumer GPU has enough memory. 52 devices with unified memory can run Pantheon Reasoning 26B A4B 1.1 v2, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Pro M2 Ultra (64 GB).
64–80 GB
fits · 9.9 GB free · up to 256K ctx
3 Mac classes · 1 device family
M2 Ultra*64 GB~41Simulate output on Mac Pro M2 Ultra (64 GB)M5 Max64 GB~33Simulate output on Mac Studio M5 Max (64 GB)Orin~13Simulate output on NVIDIA Jetson AGX Orin 64GB
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.8 27BAlibaba | 122.1 | 17.9 GB | ~38 | same size |
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | same size |
| Qwen3.5 27BAlibaba | 103.8 | 17.9 GB | ~38 | same size |
| Gemma 3 27B ITGoogle | 79.4 | 21.7 GB | ~36 | same size |
| Gemma 2 27B ITGoogle | 72.7 | 19.5 GB | ~37 | same size |
| Gemma 4 26B A4BGoogle | — | 16.9 GB | ~153 | same size |
Specifications
- Publisher
- Gryphe
- Parameters
- 26.5B
- Active parameters
- 5.1B per token
- Architecture
- Gemma4ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-09-08
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Pantheon Reasoning 26B A4B 1.1 v2 need?
Pantheon Reasoning 26B A4B 1.1 v2 requires 53.7 GB of VRAM at BF16. Full 262K context adds up to 8.7 GB (62.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 26.5B × 16 bits ÷ 8 = 53.1 GB
KV Cache + Overhead ≈ 0.6 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 ≈ 9.3 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Pantheon Reasoning 26B A4B 1.1 v2?
No — Pantheon Reasoning 26B A4B 1.1 v2 requires at least 53.7 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Pantheon Reasoning 26B A4B 1.1 v2 on a Mac?
Yes — Mac Pro M2 Ultra (64 GB) and 41 other Macs can run Pantheon Reasoning 26B A4B 1.1 v2. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 53.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run Pantheon Reasoning 26B A4B 1.1 v2 locally?
Yes — Pantheon Reasoning 26B A4B 1.1 v2 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Pantheon Reasoning 26B A4B 1.1 v2?
At BF16, Pantheon Reasoning 26B A4B 1.1 v2 can reach ~123 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 10.4 GB active ÷ (8000 × 0.65) = 2.00 ms, plus 30 layers × 0.055 ms = 1.65 ms, so 1000 ÷ 3.65 ms = ~274 tok/s
Estimated speed at BF16 (53.7 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 26B A4B 1.1 v2?
At BF16, the download is about 53.09 GB.
Which GPUs can run Pantheon Reasoning 26B A4B 1.1 v2?
No single consumer GPU has enough VRAM to run Pantheon Reasoning 26B A4B 1.1 v2 at BF16 (53.7 GB). Multi-GPU or professional hardware is required.
Which devices can run Pantheon Reasoning 26B A4B 1.1 v2?
52 devices with unified memory can run Pantheon Reasoning 26B A4B 1.1 v2 at BF16 (53.7 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.