llmrun
gnaniNemotronHForCausalLM

Gnani Evon V3.3 30B A3B — Hardware Requirements & GPU Compatibility

ChatReasoningFunctions

Gnani Evon V3.3 30B A3B is a 31.7B-parameter open language model from gnani. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 20.95 GB of VRAM — see which GPUs and Macs can run it below.

31.7B params · MoE3.8B active131K contextApache 2.041.8K downloads64 likes
S

Runs great on a 24 GB GPU

Runs on24 GB Q4_K_M · ~156 tok/s · 8KMacs from24 GB Q2_K · ~56 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Gnani Evon V3.3 30B A3B

One recommended way. Every other method, OS and quant is in the step-by-step guide.

Recommended

vLLM
one command · needs vLLM installed
$vllm serve gnani/gnani-evon-v3.3-30B-A3B --max-model-len 16384

vLLM repo with its own quantisation

Download: Weights on Hugging Face

install, OS, other quants

Other ways

each opens step-by-step

Run in cloud

Fits on RTX PRO 4500 (32 GB) (7 GB headroom) · Q4_K_M

Generation speed
~145 tok/s
generation speed
Cost per 1M output tokens
$0.65
per 1M output tokens
Deployon RunPodBest optionfrom $0.34/hr (opens in new tab)
Compare GPUs →
or

How Much VRAM Does Gnani Evon V3.3 30B A3B Need?

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

QuantizationVRAM+32KOn RTX 4090 (reference)
14.8 GB22.9 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~188 tok/s
17.0 GB25.1 GB3-bit medium — 3-bit medium quantizationFits: 16K context · ~175 tok/s
20.9 GB29 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 8K context · ~156 tok/s
24.9 GB33 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffDoes not fit: needs 28.7 GB
28.8 GB36.9 GB6-bit, very good — 6-bit quantization, very good qualityDoes not fit: needs 32.6 GB
34.9 GB43 GB8-bit, near-lossless — 8-bit quantization, near-losslessDoes not fit: needs 38.7 GB
69.8 GB77.9 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingDoes not fit: needs 73.6 GB
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

24.7GBat 16K context

Weights
20.1 GB
KV cache
4.3 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · fits up to 8K context · ~156 tok/s

≥50 tok/s needs ≥219 GB/s · RTX 5090 ~210, M3 Ultra ~72

Which Hardware Can Run Gnani Evon V3.3 30B A3B?

Q4_K_M · 20.9 GB

Gnani Evon V3.3 30B A3B (Q4_K_M) requires 20.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 28+ GB is recommended. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 100 devices with unified memory can run Gnani Evon V3.3 30B A3B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8–16 GB · RTX 4060, RTX 3060 12GB, RTX 5060 Ti 16GBDoesn't fit — smallest quant needs 18.6 GB8 GB tier →12 GB tier →16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 24.7 GB · ~156 tok/s · 8Ktight24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 24.7 GB · ~26 tok/s · 16KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 24.7 GB · ~62 tok/s · 128KMacs →

Alternatives to Gnani Evon V3.3 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
gnani
Parameters
31.7B
Active parameters
3.8B per token
Architecture
NemotronHForCausalLM
Context Length
131,072 tokens
Vocabulary Size
163,072
Release Date
2026-08-10
License
Apache 2.0

Resources

Frequently Asked Questions

How much VRAM does Gnani Evon V3.3 30B A3B need?

Gnani Evon V3.3 30B A3B requires 20.9 GB of VRAM at Q4_K_M, or 69.8 GB at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 31.7B × 4.8 bits ÷ 8 = 19 GB

KV Cache + Overhead ≈ 1.9 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.

VRAM usage by quantization

20.9 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run Gnani Evon V3.3 30B A3B?

Yes, at Q4_K_M (20.9 GB) or lower. Higher quantizations like Q5_K_M (24.9 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Gnani Evon V3.3 30B A3B?

For Gnani Evon V3.3 30B A3B, Q4_K_M (20.9 GB) offers the best balance of quality and VRAM usage. Q5_K_M (24.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 14.8 GB.

VRAM requirement by quantization

Q2_K
14.8 GB
Q4_K_M ★
20.9 GB
Q5_K_M
24.9 GB
Q6_K
28.8 GB
Q8_0
34.9 GB
BF16
69.8 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Gnani Evon V3.3 30B A3B on a Mac?

Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Gnani Evon V3.3 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 20.9 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).

Can I run Gnani Evon V3.3 30B A3B locally?

Yes — Gnani Evon V3.3 30B A3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Gnani Evon V3.3 30B A3B?

At Q4_K_M, Gnani Evon V3.3 30B A3B can reach ~99 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~156 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 → 2.5 GB active ÷ (8000 × 0.65) = 0.48 ms, plus 48 layers × 0.055 ms = 2.64 ms, so 1000 ÷ 3.12 ms = ~321 tok/s

Estimated speed at Q4_K_M (20.9 GB)

~321 tok/s
~156 tok/s
~321 tok/s
~293 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 Gnani Evon V3.3 30B A3B?

At Q4_K_M, the download is about 19.05 GB. The full-precision BF16 version is 63.50 GB. The smallest option (Q2_K) is 13.49 GB.

Which GPUs can run Gnani Evon V3.3 30B A3B?

7 consumer GPUs can run Gnani Evon V3.3 30B A3B 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 Gnani Evon V3.3 30B A3B?

100 devices with unified memory can run Gnani Evon V3.3 30B A3B at Q4_K_M (20.9 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.