llmrun
ServiceNow-AILlavaForConditionalGeneration

Apriel 1.6 15B Thinker — Hardware Requirements & GPU Compatibility

VisionFunctions

Apriel 1.6 15B Thinker is ServiceNow's 15-billion-parameter multimodal reasoning model, an update from Apriel-1.5-15B-Thinker that processes both text and images. Post-trained using supervised fine-tuning and reinforcement learning, the card reports a score of 57 on the Artificial Analysis index and shows over 30 percent less reasoning token usage compared to version 1.5. The documentation notes it fits on a single GPU, making quantized versions practical for mainstream consumer cards. The context window holds 262,400 tokens. Released under the MIT license, it allows unrestricted commercial and research use. Published in November 2025, it replaces Apriel-1.5-15B-Thinker with a simplified chat template plus four new special tokens designed to simplify parsing tool calls and final responses.

14.9B params · dense262K contextMIT1.5K downloads308 likes4.4K quant downloads
S

Runs great on a 24 GB GPU

Runs from12 GB Q4_K_M · 8KBest on24 GB Q4_K_M · ~67 tok/s · 32KMacs from16 GB Q4_K_M · ~14 tok/s

MIT

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Apriel 1.6 15B Thinker

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

Ollama
one command · needs Ollama installed
$ollama run hf.co/bartowski/ServiceNow-AI_Apriel-1.6-15b-Thinker-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 10.8 GB free · 16K context

Download: ServiceNow-AI_Apriel-1.6-15b-Thinker-Q4_K_M.gguf8.79 GBbartowski

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 24 GB GPU

  • The easiest way to try this model
  • Running in a few minutes, easy setup
  • Chat right here or connect any app

$5+ bonus for new users

How Much VRAM Does Apriel 1.6 15B Thinker Need?

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

QuantizationVRAM+32KOn RTX 4090 (reference)
7.1 GB14.7 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 64K context · ~92 tok/s
7.3 GB14.9 GB3-bit small — 3-bit small quantizationFits: 64K context · ~90 tok/s
8.1 GB15.6 GB3-bit medium — 3-bit medium quantizationFits: 64K context · ~81 tok/s
8.2 GB15.8 GB4-bit · legacy — 4-bit legacy quantizationFits: 64K context · ~80 tok/s
9.7 GB17.3 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 32K context · ~67 tok/s
11.4 GB18.9 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 32K context · ~58 tok/s
13.1 GB20.6 GB6-bit, very good — 6-bit quantization, very good qualityFits: 32K context · ~50 tok/s
15.7 GB23.2 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 32K context · ~42 tok/s

Selected Q4_K_M

4-bit medium quantization

13.2GBat 16K context

Weights
8.9 GB
KV cache
4.0 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 10.8 GB free · ~67 tok/s

≥50 tok/s needs ≥747 GB/s · RTX 5090 ~120, M5 Ultra ~88

Which Hardware Can Run Apriel 1.6 15B Thinker?

Q4_K_M · 9.7 GB

Apriel 1.6 15B Thinker (Q4_K_M) requires 9.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 13+ GB is recommended. Using the full 262K context window can add up to 64.0 GB, bringing total usage to 73.7 GB. 51 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 12GB. 171 devices with unified memory can run Apriel 1.6 15B Thinker, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), Mac Mini M2 Pro (16 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Doesn't fit — smallest quant needs 8.4 GB8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 13.2 GB · ~24 tok/s · 8Ktight12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 13.2 GB · ~30 tok/s · 16K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 13.2 GB · ~67 tok/s · 32K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 13.2 GB · ~9 tok/s · 64KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 13.2 GB · ~39 tok/s · 128KMacs →

Alternatives to Apriel 1.6 15B Thinker

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Phi 4 ReasoningMicrosoft—12.5 GB~69same size
Phi 3 Medium 128k InstructMicrosoft—12 GB~72same size
Qwen1.5 14BAlibaba—22.2 GB~63same size
Nemotron Terminal 14BNVIDIA—11.9 GB~69same size
Ministral 3 14B Reasoning 2512Mistral AI—12 GB~72same size
Qwen3 14B BaseAlibaba—11.9 GB~69same size
Fine-tunes & variants(1)

Specifications

Publisher
ServiceNow-AI
Parameters
14.9B
Architecture
LlavaForConditionalGeneration
Context Length
262,400 tokens
Vocabulary Size
131,072
Release Date
2025-11-28
License
MIT

Frequently Asked Questions

How much VRAM does Apriel 1.6 15B Thinker need?

Apriel 1.6 15B Thinker requires 9.7 GB of VRAM at Q4_K_M, or 30.5 GB at BF16. Full 262K context adds up to 64.0 GB (73.7 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 14.9B × 4.8 bits ÷ 8 = 8.9 GB

KV Cache + Overhead ≈ 0.8 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 ≈ 64.8 GB (at full 262K context)

VRAM usage by quantization

9.7 GB
73.7 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run Apriel 1.6 15B Thinker?

Yes, at Q8_0 (15.7 GB) or lower. Higher quantizations like BF16 (30.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Apriel 1.6 15B Thinker?

For Apriel 1.6 15B Thinker, Q4_K_M (9.7 GB) offers the best balance of quality and VRAM usage. Q4_K_L (9.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 4.9 GB.

VRAM requirement by quantization

IQ2_XXS
4.9 GB
IQ3_XS
6.9 GB
Q3_K_L
8.4 GB
Q4_K_M ★
9.7 GB
Q4_K_L
9.9 GB
BF16
30.5 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Apriel 1.6 15B Thinker on a Mac?

Yes — Mac Mini M2 Pro (16 GB) and 145 other Macs can run Apriel 1.6 15B Thinker. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 9.7 GB of usable unified memory (RAM minus macOS overhead).

Can I run Apriel 1.6 15B Thinker locally?

Yes — Apriel 1.6 15B Thinker can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Apriel 1.6 15B Thinker?

At Q4_K_M, Apriel 1.6 15B Thinker can reach ~494 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~67 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 ÷ 9.72 × 0.65 = ~535 tok/s

Estimated speed at Q4_K_M (9.7 GB)

~535 tok/s
~67 tok/s
~535 tok/s
~494 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 Apriel 1.6 15B Thinker?

At Q4_K_M, the download is about 8.92 GB. The full-precision BF16 version is 29.73 GB. The smallest option (IQ2_XXS) is 4.09 GB.

Which GPUs can run Apriel 1.6 15B Thinker?

51 consumer GPUs can run Apriel 1.6 15B Thinker at Q4_K_M. Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 30 GPUs have plenty of headroom for comfortable inference.

Which devices can run Apriel 1.6 15B Thinker?

171 devices with unified memory can run Apriel 1.6 15B Thinker at Q4_K_M (9.7 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.