Skip to content

Inkling 2 Small VRAM Requirements

Thinking Machines Lab, United States · Released November 4, 2026New

Inkling 2 Small has 594.0B parameters (17B active per token). In BF16 its weights alone take 1107 GiB; quantized to 4-bit, about 334 GiB. Each 32K-token request adds 1.16 GiB of KV cache. Cheapest way to run it today: 8 × RTX A6000 (48 GB) at $3.21 per hour. It reads text and images, calls tools and lets you set its reasoning effort.

Size your own setup in the calculator →

Inkling 2 Small at a glance

Made by
Thinking Machines Lab, United States
Released
November 4, 2026
Parameters
594.0B, 17B active
Context window
1M tokens
License
Apache 2.0, commercial use allowed
Reads
Text and images
Tool calling
Supported
Reasoning
Adjustable reasoning effort
Training
2.1 × 1023 FLOP · 13 trillion tokens · 2,048 × NVIDIA GB300 (Blackwell Ultra)

Epoch AI (opens in a new tab), likely estimate, CC BY 4.0

Runs with
vLLM, SGLang, llama.cpp (Ollama, LM Studio), MLX (Mac) · vLLM recipe (opens in a new tab)

VRAM by precision and context length

Weights plus the KV cache of one request (BF16 cache) and the model's fixed recurrent state, in GiB. Add 1 to 3 GiB for the inference engine itself.

Weights formatWeights only+ 8K context+ 32K context+ 128K context+ 1M context
NVFP4 / MXFP8 experts + BF16 (native)363364364367395
BF16 / FP1611071107110811111139
FP8 / INT8555555556559587
4-bit (GGUF Q4_K_M)334334335338366

Inkling 2 Small GGUF files

Exact size of each quantization in bartowski/Inkling-2-Small-GGUF (opens in a new tab), and the smallest GPU that runs it with llama.cpp, Ollama or LM Studio and an 8K-token context.

QuantizationFile sizeSmallest GPU
Q8_0588 GiBMore than 96 GB: see the calculator
Q6_K487 GiBMore than 96 GB: see the calculator
Q5_K_M423 GiBMore than 96 GB: see the calculator
Q4_K_M344 GiBMore than 96 GB: see the calculator
IQ4_XS300 GiBMore than 96 GB: see the calculator
Q3_K_M261 GiBMore than 96 GB: see the calculator
Q2_K210 GiBMore than 96 GB: see the calculator
IQ1_S119 GiBMore than 96 GB: see the calculator
Show the other 16 files
QuantizationFile sizeSmallest GPU
Q6_K_S465 GiBMore than 96 GB: see the calculator
Q5_K_S391 GiBMore than 96 GB: see the calculator
Q4_1346 GiBMore than 96 GB: see the calculator
IQ4_NL344 GiBMore than 96 GB: see the calculator
Q4_K_S322 GiBMore than 96 GB: see the calculator
Q4_0313 GiBMore than 96 GB: see the calculator
Q3_K_L296 GiBMore than 96 GB: see the calculator
IQ3_M270 GiBMore than 96 GB: see the calculator
IQ3_XS247 GiBMore than 96 GB: see the calculator
Q3_K_S247 GiBMore than 96 GB: see the calculator
IQ3_XXS229 GiBMore than 96 GB: see the calculator
IQ2_M195 GiBMore than 96 GB: see the calculator
IQ2_S175 GiBMore than 96 GB: see the calculator
IQ2_XS166 GiBMore than 96 GB: see the calculator
IQ2_XXS155 GiBMore than 96 GB: see the calculator
IQ1_M134 GiBMore than 96 GB: see the calculator

Read every day from Hugging Face. Split files are added together; vision projectors are left out.

How many GPUs to run Inkling 2 Small

Fewest GPUs that fit the weights plus one 8K-token request. Data-center GPUs use vLLM (90% of memory usable), the others llama.cpp. Several GPUs split the model with tensor or pipeline parallelism.

GPUNVFP4 / MXFP8 experts + BF16 (native)BF16 / FP168-bit4-bit
GeForce RTX 4090 24 GBNot on this GPU64 (several machines)32 (several machines)16 (several machines)
GeForce RTX 5090 32 GBNot on this GPU48 (several machines)24 (several machines)16 (several machines)
RTX PRO 6000 Blackwell 96 GBNot on this GPU16 (several machines)64
Mac M5 Max 128 GB 96 GB usableNot on this GPU16 (several machines)64
Ryzen AI Max+ 395 128 GB 96 GB usableNot on this GPU16 (several machines)64
DGX Spark (GB10) 128 GBNot on this GPU16 (several machines)53
NVIDIA H100 80 GBNot on this GPU24 (several servers)16 (several servers)6
NVIDIA H200 141 GBNot on this GPU16 (several servers)53
NVIDIA B200 (HGX) 180 GB3843

8-bit: FP8 with vLLM (INT8 on GPUs without FP8), Q8_0 with llama.cpp. 4-bit: AWQ / GPTQ with vLLM, Q4_K_M with llama.cpp, both counted at the Q4_K_M size. Not on this GPU: the official NVFP4 / MXFP8 experts + BF16 weights do not run there (llama.cpp needs a GGUF version, and vLLM needs a GPU with FP4 support).

Cheapest way to run Inkling 2 Small today

For each GPU: the fewest cards that fit Inkling 2 Small with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-11-22).

On-demand prices from AWS, Google Cloud, Azure, RunPod, Vast.ai, Oracle Cloud, OVHcloud, Scaleway, Verda, Akash and UpCloud, checked every hour. Serving many users needs more KV cache, so more memory: size it in the calculator. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.

AWS, Google Cloud and UpCloud prices: Spare Cores (opens in a new tab), CC BY-SA 4.0 (opens in a new tab), shared under the same license.

Or use Inkling 2 Small through an API

No GPU to rent: these providers serve Inkling 2 Small and bill per token. Speeds are measured by Hugging Face for one request.

ProviderOutput, per 1M tokensInput, per 1MSpeedFirst token
Primeintellect$0.500$0.150349 tokens/s364 ms
DeepInfra$0.950$0.285166 tokens/s1.1 s
Cloudflare$1.00$0.300100 tokens/s5.6 s
Modal$1.00$0.300218 tokens/s413 ms
Nebius$1.00$0.300102 tokens/s374 ms
Together AI$1.00$0.300263 tokens/s690 ms

Prices and speeds from Hugging Face Inference Providers (opens in a new tab), read every day (November 22, 2026). An API wins at low volume; renting GPUs wins when they stay busy: the calculator gives the break-even.

Recommended settings for Inkling 2 Small

Reasoning. Adjustable reasoning effort. Reasoning tokens take context and KV cache like any other token: leave room for them.

KV cache: how memory grows with context

Architecture: MoE 384 experts · 8 global layers + 40 sliding-window layers (1024 tokens), GQA 8 KV × 128, relative-bias attention · short convolutions · image input. Its KV cache is 5.2× smaller than if every layer used full attention, because only 40 of its 48 layers keep a KV cache; the others hold a small fixed-size state. Only 17B parameters are active per token, but all 594B must sit in memory: VRAM depends on the total, speed on the active part.

Context per requestBF16 cacheFP8 cache
8K tokens0.41 GiB0.20 GiB
32K tokens1.16 GiB0.58 GiB
128K tokens4.16 GiB2.08 GiB
1M tokens32.2 GiB16.1 GiB

Plus 6.00 MiB of recurrent state per request, whatever the context.

Inkling 2 Small VRAM FAQ

How much VRAM does Inkling 2 Small need?

In BF16 the weights alone take 1107 GiB (1188 GB). In FP8 that is 555 GiB, and about 334 GiB with 4-bit quantization (Q4_K_M); the official NVFP4 / MXFP8 experts + BF16 checkpoint is 363 GiB. Each request then adds KV cache: 0.41 GiB at 8K tokens and 1.16 GiB at 32K (BF16 cache).

Can Inkling 2 Small run on a single RTX 4090 (24 GB)?

No. Even in 4-bit it needs 16 RTX 4090s, spread over several machines. In 4-bit it needs 6 H100 GPUs.

Can Inkling 2 Small run on an RTX 5090 (32 GB)?

No. Even in 4-bit it needs 16 RTX 5090s, spread over several machines.

Can Inkling 2 Small run on a Mac?

Yes. In 4-bit (Q4_K_M with llama.cpp) it needs a Mac with 512 GB of unified memory, of which macOS gives the GPU about 384 GB, for one request with an 8K-token context. In 8-bit it does not fit on a single Mac.

Can Inkling 2 Small run on a DGX Spark or a Ryzen AI Max+ 395 (128 GB)?

No. Even in 4-bit it needs 3 DGX Spark units or 4 Ryzen AI Max+ 395 machines (128 GB), linked over the network.

What is the cheapest way to run Inkling 2 Small?

On 2026-11-22, the cheapest on-demand setup is 8 × RTX A6000 (48 GB) with Q4_K_M weights on Vast.ai, at $3.21 per hour (about $2,341.84 per month). Next: 8 × RTX 6000 Ada (48 GB) with Q4_K_M weights on Vast.ai, at $4.31 per hour. Sized for one 8K-token request; prices are checked every hour.

How many H100 GPUs does Inkling 2 Small need?

With one request and an 8K-token context: 24 in BF16, 16 in FP8 and 6 in 4-bit (vLLM, 90% of memory usable). Above 8 GPUs, that means several servers. Serving many users at once needs more memory for their KV caches: the calculator sizes that for you.

Can Inkling 2 Small read images?

Yes. Inkling 2 Small reads text and images. Images add tokens to the context, so they also add KV cache.

Does Inkling 2 Small support tool calling?

Yes, Inkling 2 Small supports tool (function) calling: it can ask your application to run a function and use the result.

Does Inkling 2 Small have a thinking mode?

Adjustable reasoning effort. Reasoning tokens count toward the context and the KV cache.

Inkling 2 Small VRAM badge

For a model card or a README: the 4-bit size and the smallest GPU it fits on, linked to this page. Data as JSON: /api/models/inkling-2-small.json.

Inkling 2 Small VRAM badge

[![Inkling 2 Small VRAM](https://studiotvai.com/badge/inkling-2-small.svg)](https://studiotvai.com/vram-requirements/inkling-2-small)

Other models

Same family (large moe): MiniMax M3.1 Flash · MiniMax M3 · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · Atria Dawn · Hydrogen-1.0 · Atria Dawn Preview · Hy4 Preview · Hy4 Flash · K-EXAONE 2.0 750B-A37B · Inkling · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · LongCat-2.0 · LongCat-2.5 · ERNIE 5.5 Flash Base · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Muse Spark Open · Beam 1.0 501B-A23B · Kimi K3 · Mistral Large 4 · Mistral Large 3 · Mistral Small 4 119B · Leanstral 1.5 119B-A6B · Mixtral 8x22B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Intern S2 397B · DeepSeek V3 · DeepSeek V3.1 · Kimi K2.7 Code · Kimi K2.5 · Kimi K2 · GLM-5.2 · GLM-5.1 · GLM-5 · MiniMax M2.5 · MiniMax M2 · MiMo-V2.5 · Ornith-1.0 397B · Qwen3 235B-A22B · Qwen3.5 397B-A17B · GLM-4.7 · GLM-4.5 · Ling-3.1-flash · Step 5 Preview · Hy3 · Kimi K3.1 Pro · DeepSeek V3.2 · Laguna M.1 · Qwen3-VL 235B-A22B · Nex-N2.6 · Sage-S2.1 · Hy3-preview · Hy4

All 233 other models

Llama 3.1 8B · Llama 3 8B · Llama 3.2 3B · Nanbeige4.3 33B · Granite 4.2 30B · Granite 4.2 8B · Granite 4.2 3B · MiniCPM5 2B · MiniCPM5 1B · Ministral 3 14B · Ministral 3 8B · Ministral 3 3B · Devstral 2 123B · Devstral Small 2 24B · Mistral Medium 3.5 128B · Magistral Small 1.2 24B · Mistral Small 3 24B · Mistral Large 2411 123B · Pixtral Large 124B · Codestral 22B · Mistral Small 2409 22B · Pixtral 12B · Nemotron 3.5 Parse · Gemma 2 9B · Gemma 3 4B · Gemma 3 12B · Gemma 3 27B · LLaVA 1.6 Mistral 7B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 70B · Llama 3.1 405B · Hy-Memory 30B-A3B · Kimi VL A3B Instruct · Mixtral 8x7B · Unlimited-OCR · Unlimited-OCR 2 · Xing4.0 29B-A4B · Qwen3.5 4B · MiniCPM-V-4.7 1B · Raon-1 mini preview · Raon-1 nano · Qwen3.5 9B · Qwen3.8 27B · Qwen3.6 35B-A3B · Maxwell V1 Flash · Clover 35B-A3B Preview · SenseNova Loop 9B Preview · Qwen3.5 122B-A10B · Qwen3.8-Flash-Next · Qwen3.8-Flash-Next E384 FP4 V2 · LFM3 1.7B · LFM3-VL 2B · d1 2B · LFM2.5 8B-A1B · LFM2 24B-A2B · Gemma 4 12B · Gemma 4 31B · Gemma 4 26B-A4B · gpt-oss 20B · gpt-oss 120B · Llama 4 Scout 17B-16E · Llama 4 Maverick 17B-128E · Kolibri-1 · Recursive Flint · Nemotron Labs Dory 1.0 4B · Step 3.5 Flash · Step 3.7 Flash · Laguna S 2.1 · Laguna XS 2.1 · Command A+ · Inkling Small · Muse Glimmer 30B · Nemotron 3 Nano 30B-A3B · Nemotron 3 Super 120B-A12B · Nemotron 3 Ultra 550B-A55B · Mamba-Codestral 7B · Nemotron 3.5 Super VL 120B-A12B · Nemotron 3.5 Bolt 74B-A9B · MiniMax M3.1 Flash · MiniMax M3 · MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · Atria Dawn · Hydrogen-1.0 · Atria Dawn Preview · Hy4 Preview · Hy4 Flash · K-EXAONE 2.0 750B-A37B · Inkling · Inkling 2 Mini · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · LongCat-2.0 · LongCat-2.5 · ERNIE 5.5 Flash Base · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Muse Spark Open · Beam 1.0 501B-A23B · Kimi K3 · Mistral Large 4 · Mistral Large 3 · Mistral Small 4 119B · Leanstral 1.5 119B-A6B · Mixtral 8x22B · Qwen3-Coder-Next 80B-A3B · Qwen3-Coder 30B-A3B · Qwen3-Coder 480B-A35B · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Ornith 1.5 35B-A3B · Ornith 1.5 9B · Intern S2 397B · Clef · Clef Flash · d1 3B · Humanizer · JEV 27B VL · Mellum2.1 12B-A2.5B · LightOnOCR-3 4B · Spark-X2.5 4B · Agnes-3.0-Qwen · Youtu-Parsing-Omni · Agnes-3.0-Flash · Mistral 7B v0.3 · Mistral Small 3.1 24B · Mistral Nemo · Ministral 8B · DeepSeek V3 · DeepSeek R1 Qwen3 8B · DeepSeek R1 Distill Qwen 32B · DeepSeek V3.1 · DeepSeek R1 Distill Qwen 14B · DeepSeek R1 Distill Qwen 7B · DeepSeek R1 Distill Llama 8B · Qwen3 4B · Qwen3 8B · Qwen2.5 7B · Qwen3 14B · Qwen2.5 3B · Qwen3.6 27B · Qwen3.5 27B · Qwen2.5-Coder 7B · Qwen2.5 32B · Qwen2.5-Coder 14B · Qwen3.5 35B-A3B · Qwen3 30B-A3B · Qwen2.5 14B · Qwen2.5-Coder 32B · Kimi K2.7 Code · Kimi K2.5 · Kimi K2 · GLM-5.2 · GLM-5.1 · GLM-5 · MiniMax M2.5 · MiniMax M2 · MiMo-V2.5 · Ornith-1.0 397B · Qwen2.5-Coder 3B · Qwen3 235B-A22B · Qwen3.5 397B-A17B · Gemma 4 E4B · Gemma 4 E2B · Nemotron 3 Nano 4B · Nemotron 3.5 Lightning 30B-A3B · MiniCPM-V-4.7 35B-A3B · LFM2.5 24B-A2B · GLM-4.7 · Qwen3-VL 8B · Qwen2.5-VL 7B · Qwen3-VL 4B · Qwen2.5-VL 3B · Qwen2.5-VL 32B · Qwen2-VL 7B · GLM-4.5-Air · GLM-4.5 · phi-4 · Phi-3.5-mini · Phi-4-mini · Phi-3-mini-128k · Ling-3.1-flash · Step 5 Preview · Hy3 · Ornith-1.5 122B · Spark-X2.6 4B · Sage-A1.5 · MLExpert · Agents-A1 4B · Ling-3.0-flash-Sante · MiniCPM-OCR-1.0 · WeVisOne-VL 4B · Granite 4.1 3B · Qwen3-VL 30B-A3B · Mage-VL-Cowork · Spark-X2.6 1.7B · Qwen3.5 4B-Qwenputer · Kimi K3.1 Pro · 6.8-Code2Video · Qwen3.5 4B-GLB-3D-Coder · DeepSeek V3.2 · GLM-4.7-Flash · Laguna M.1 · Laguna XS.2 · Qwen3-VL 235B-A22B · Qwen2 7B · Qwen2.5 72B · Qwen3-VL 32B · Qwen2.5 14B-1M · Qwen3-Next 80B-A3B · Qwen2.5-VL 72B · Nemotron Nano 9B v2 · Qwen3.5 0.8B-weight-space-programming · Axion-1.0 35B · Hermes-3-Llama-3.1 8B · Qwen3.8 27B-DSpine-b16 · Granite 3.3 8B · MNN-Pocket 0.3B · S5-nano · Nex-N2.6 · Sage-S2.1 · KORMo-Web 11B · Hy3-preview · ERNIE 4.5 21B-A3B · Aion-1.0 2.3B · Hy4

Estimates, not guarantees: computed from the official config.json with the same engine as the LLM VRAM Calculator. Real usage depends on your engine version and settings.