llmrun
GrypheQwen3MoeForCausalLM

Pantheon Proto RP 1.8 30B A3B — Hardware Requirements & GPU Compatibility

ChatRoleplay

Pantheon Proto RP 1.8 30B A3B is a 30.5B-parameter open language model from Gryphe. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 18.72 GB of VRAM — see which GPUs and Macs can run it below.

30.5B params · MoE3.4B active33K contextApache 2.0199 downloads29 likes
Based on Qwen3 30B A3B Base
S

Runs great on a 24 GB GPU

Runs from16 GB Q3_K_M · 16KBest on24 GB Q4_K_M · ~173 tok/s · 32KMacs from18 GB Q2_K · ~42 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Pantheon Proto RP 1.8 30B A3B

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

vLLM
one command · needs vLLM installed
$vllm serve Gryphe/Pantheon-Proto-RP-1.8-30B-A3B --max-model-len 16384

vLLM repo with its own quantisation

Download: Weights on Hugging Face

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 3090 (24 GB) (4 GB headroom) · Q4_K_M

Generation speed
~166 tok/s
generation speed
Cost per 1M output tokens
$0.33
per 1M output tokens
Deployon Vast.aiBest valuefrom $0.20/hr (opens in new tab)
Compare GPUs →
or

How Much VRAM Does Pantheon Proto RP 1.8 30B A3B Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
13.4 GB14.9 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~205 tok/s
15.3 GB16.8 GB3-bit medium — 3-bit medium quantizationFits: 32K context · ~192 tok/s
18.7 GB20.2 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 32K context · ~173 tok/s
22.1 GB23.7 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 32K context · ~157 tok/s
25.6 GB27.1 GB6-bit, very good — 6-bit quantization, very good qualityDoes not fit: needs 26.3 GB
30.9 GB32.4 GB8-bit, near-lossless — 8-bit quantization, near-losslessDoes not fit: needs 31.6 GB
61.5 GB63 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingDoes not fit: needs 62.2 GB
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

19.4GBat 16K context

Weights
18.3 GB
KV cache
0.8 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 4.6 GB free · ~173 tok/s

≥50 tok/s needs ≥182 GB/s · RTX 5090 ~227, RTX 3090 Ti ~173

Which Hardware Can Run Pantheon Proto RP 1.8 30B A3B?

Q4_K_M · 18.7 GB

Pantheon Proto RP 1.8 30B A3B (Q4_K_M) requires 18.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 25+ GB is recommended. Using the full 33K context window can add up to 1.5 GB, bringing total usage to 20.2 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Pantheon Proto RP 1.8 30B A3B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8–12 GB · RTX 4060, RTX 3060 12GBDoesn't fit — smallest quant needs 14.1 GB8 GB tier →12 GB tier →
16 GB · RTX 5060 Ti 16GBQ3_K_M · 16 GB · ~119 tok/s · 16K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 19.4 GB · ~173 tok/s · 32K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 19.4 GB · ~29 tok/s · 32KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 19.4 GB · ~67 tok/s · 32KMacs →

Alternatives to Pantheon Proto RP 1.8 30B A3B

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Hy Memory 30B A3BTencent—19.1 GB~184same size
Granite Switch 4.1 30BIBM—22.7 GB~35same size
Muse Glimmer 30BMeta—19.6 GB~36same size
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA—19.3 GB~197same size
Hy MT2 30B A3BTencent—19.1 GB~170same size
Gemma 4 31BGoogle—21.7 GB~32same size

Specifications

Publisher
Gryphe
Parameters
30.5B
Active parameters
3.4B per token
Architecture
Qwen3MoeForCausalLM
Context Length
32,768 tokens
Vocabulary Size
151,936
Release Date
2025-05-09
License
Apache 2.0

Resources

Frequently Asked Questions

How much VRAM does Pantheon Proto RP 1.8 30B A3B need?

Pantheon Proto RP 1.8 30B A3B requires 18.7 GB of VRAM at Q4_K_M, or 61.5 GB at BF16. Full 33K context adds up to 1.5 GB (20.2 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 30.5B × 4.8 bits ÷ 8 = 18.3 GB

KV Cache + Overhead ≈ 0.4 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 ≈ 1.9 GB (at full 33K context)

VRAM usage by quantization

18.7 GB
20.2 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run Pantheon Proto RP 1.8 30B A3B?

Yes, at Q5_K_M (22.1 GB) or lower. Higher quantizations like Q6_K (25.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Pantheon Proto RP 1.8 30B A3B?

For Pantheon Proto RP 1.8 30B A3B, Q4_K_M (18.7 GB) offers the best balance of quality and VRAM usage. Q5_K_M (22.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 13.4 GB.

VRAM requirement by quantization

Q2_K
13.4 GB
Q4_K_M ★
18.7 GB
Q5_K_M
22.1 GB
Q6_K
25.6 GB
Q8_0
30.9 GB
BF16
61.5 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Pantheon Proto RP 1.8 30B A3B on a Mac?

Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run Pantheon Proto RP 1.8 30B A3B, the smallest at Q2_K. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 18.7 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).

Can I run Pantheon Proto RP 1.8 30B A3B locally?

Yes — Pantheon Proto RP 1.8 30B A3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Pantheon Proto RP 1.8 30B A3B?

At Q4_K_M, Pantheon Proto RP 1.8 30B A3B can reach ~100 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~173 tok/s. 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 → 2.1 GB active ÷ (8000 × 0.65) = 0.39535 ms, plus 48 layers × 0.055 ms = 2.64000 ms, so 1000 ÷ 3.03535 ms = ~329 tok/s

Estimated speed at Q4_K_M (18.7 GB)

~330 tok/s
~173 tok/s
~330 tok/s
~304 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Pantheon Proto RP 1.8 30B A3B?

At Q4_K_M, the download is about 18.32 GB. The full-precision BF16 version is 61.06 GB. The smallest option (Q2_K) is 12.98 GB.

Which GPUs can run Pantheon Proto RP 1.8 30B A3B?

8 consumer GPUs can run Pantheon Proto RP 1.8 30B A3B at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.

Which devices can run Pantheon Proto RP 1.8 30B A3B?

122 devices with unified memory can run Pantheon Proto RP 1.8 30B A3B at Q4_K_M (18.7 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.