Skip to content

MNN-Pocket 0.3B VRAM Requirements

Alibaba (MNN), China · Released September 23, 2026

MNN-Pocket 0.3B has 0.36B parameters. In BF16 its weights alone take 0.67 GiB; quantized to 4-bit, about 0.25 GiB. Each 32K-token request adds 0.44 GiB of KV cache. Cheapest way to run it today: 1 × RTX A4000 (16 GB) at $0.088 per hour. It calls tools.

Size your own setup in the calculator →

MNN-Pocket 0.3B at a glance

Made by
Alibaba (MNN), China
Released
September 23, 2026
Parameters
0.36B
Context window
128K tokens, with YaRN (32K native)
License
Apache 2.0, commercial use allowed
Reads
Text only
Tool calling
Supported
Languages
English, Chinese
Runs with
vLLM, SGLang, llama.cpp (Ollama, LM Studio), MLX (Mac)
Checked against

KV cache matches the GGUF header of taobao-mnn/MNN-Pocket-0.3B-GGUF (opens in a new tab) (what llama.cpp allocates), November 22, 2026

VRAM by precision and context length

Weights plus the KV cache of one request (BF16 cache), in GiB. Add 1 to 3 GiB for the inference engine itself.

Weights formatWeights only+ 8K context+ 32K context+ 128K context
BF16 / FP160.670.781.112.42
FP8 / INT80.390.500.832.14
4-bit (GGUF Q4_K_M)0.250.360.692.00

MNN-Pocket 0.3B GGUF files

Exact size of each quantization in taobao-mnn/MNN-Pocket-0.3B-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
F160.68 GiBRTX 4060 (8 GB)
Q8_00.36 GiBRTX 4060 (8 GB)
Q4_10.18 GiBRTX 4060 (8 GB)

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

How many GPUs to run MNN-Pocket 0.3B

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.

GPUBF16 / FP168-bit4-bit
GeForce RTX 4090 24 GB111
GeForce RTX 5090 32 GB111
RTX PRO 6000 Blackwell 96 GB111
Mac M5 Max 128 GB 96 GB usable111
Ryzen AI Max+ 395 128 GB 96 GB usable111
DGX Spark (GB10) 128 GB111
NVIDIA H100 80 GB111
NVIDIA H200 141 GB111
NVIDIA B200 (HGX) 180 GB111

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.

Cheapest way to run MNN-Pocket 0.3B today

For each GPU: the fewest cards that fit MNN-Pocket 0.3B 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.

KV cache: how memory grows with context

Architecture: 28 layers · 28 full attention (2 KV × 64) · 32K native, 128K with YaRN. Every layer keeps keys and values for every token (grouped-query attention), so the cache grows linearly with context.

Context per requestBF16 cacheFP8 cache
8K tokens0.11 GiB0.05 GiB
32K tokens0.44 GiB0.22 GiB
128K tokens1.75 GiB0.88 GiB

MNN-Pocket 0.3B VRAM FAQ

How much VRAM does MNN-Pocket 0.3B need?

In BF16 the weights alone take 0.67 GiB (0.7 GB). In FP8 that is 0.39 GiB, and about 0.25 GiB with 4-bit quantization (Q4_K_M). Each request then adds KV cache: 0.11 GiB at 8K tokens and 0.44 GiB at 32K (BF16 cache).

Can MNN-Pocket 0.3B run on a single RTX 4090 (24 GB)?

Yes. In BF16 it fits on one RTX 4090 with an 8K-token context (0.78 GiB including the cache, with llama.cpp).

Can MNN-Pocket 0.3B run on an RTX 5090 (32 GB)?

Yes. In BF16 (0.78 GiB with an 8K-token context) it fits on one RTX 5090, with llama.cpp.

Can MNN-Pocket 0.3B run on a Mac?

Yes. In 4-bit (Q4_K_M with llama.cpp) it needs a Mac with 8 GB of unified memory or more, of which macOS gives the GPU about 5 GB, for one request with an 8K-token context. The same Mac also holds it in 8-bit (Q8_0).

Can MNN-Pocket 0.3B run on a DGX Spark or a Ryzen AI Max+ 395 (128 GB)?

Yes. In BF16 (0.78 GiB with an 8K-token context) it fits on a DGX Spark (128 GB) and on a Ryzen AI Max+ 395 with 128 GB, whose GPU gets up to 96 GB, with llama.cpp and one request.

What is the cheapest way to run MNN-Pocket 0.3B?

On 2026-11-22, the cheapest on-demand setup is 1 × RTX A4000 (16 GB) with BF16 weights on Vast.ai, at $0.088 per hour (about $64.24 per month). Next: 1 × NVIDIA L4 (24 GB) with BF16 weights on Vast.ai, at $0.104 per hour. Sized for one 8K-token request; prices are checked every hour.

How many H100 GPUs does MNN-Pocket 0.3B need?

With one request and an 8K-token context: 1 in BF16, 1 in FP8 and 1 in 4-bit (vLLM, 90% of memory usable). Serving many users at once needs more memory for their KV caches: the calculator sizes that for you.

Does MNN-Pocket 0.3B support tool calling?

Yes, MNN-Pocket 0.3B supports tool (function) calling: it can ask your application to run a function and use the result.

MNN-Pocket 0.3B 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/mnn-pocket-0-3b.json.

MNN-Pocket 0.3B VRAM badge

[![MNN-Pocket 0.3B VRAM](https://studiotvai.com/badge/mnn-pocket-0-3b.svg)](https://studiotvai.com/vram-requirements/mnn-pocket-0-3b)

Other models

Same family (dense): 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 · LLaVA 1.6 Mistral 7B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 70B · Llama 3.1 405B · Youtu-Parsing-Omni · Mistral 7B v0.3 · Mistral Small 3.1 24B · Mistral Nemo · DeepSeek R1 Qwen3 8B · DeepSeek R1 Distill Qwen 32B · 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 · Qwen2.5 32B · Qwen2.5 14B · Qwen3-VL 8B · Qwen2.5-VL 7B · Qwen3-VL 4B · Qwen2.5-VL 3B · Qwen2.5-VL 32B · Qwen2-VL 7B · phi-4 · Phi-3.5-mini · Phi-4-mini · Phi-3-mini-128k · WeVisOne-VL 4B · Granite 4.1 3B · Mage-VL-Cowork · Qwen2 7B · Qwen2.5 72B · Qwen3-VL 32B · Qwen2.5 14B-1M · Qwen2.5-VL 72B · Hermes-3-Llama-3.1 8B · Granite 3.3 8B · KORMo-Web 11B · ERNIE 4.5 21B-A3B

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 Small · 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 · 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.