llmrun
OuteAIMistralForCausalLM

Lite Oute 1 300M — Hardware Requirements & GPU Compatibility

Chat

Lite Oute 1 300M is a 300M-parameter open language model from OuteAI. It supports a context window of up to 4,096 tokens. At Q4_K_M it needs about 0.55 GB of VRAM — see which GPUs and Macs can run it below.

300M params · dense4K contextApache 2.038.7K downloads9 likes
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 4KBest on24 GB Q4_K_M · ~1191 tok/s · 4KMacs from8 GB Q4_K_M · ~130 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Lite Oute 1 300M

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 OuteAI/Lite-Oute-1-300M --max-model-len 4096

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 3060 12GB (11 GB headroom) · Q4_K_M

Generation speed
~426 tok/s
generation speed
Cost per 1M output tokens
$0.041
per 1M output tokens

How Much VRAM Does Lite Oute 1 300M Need?

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

QuantizationVRAM+32KOn RTX 4090 (reference)
0.5 GB—2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 4K context · ~1310 tok/s
0.5 GB—3-bit medium — 3-bit medium quantizationFits: 4K context · ~1260 tok/s
0.6 GB—4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 4K context · ~1191 tok/s
0.6 GB—5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 4K context · ~1111 tok/s
0.6 GB—6-bit, very good — 6-bit quantization, very good qualityFits: 4K context · ~1057 tok/s
0.7 GB—8-bit, near-lossless — 8-bit quantization, near-losslessFits: 4K context · ~978 tok/s
1.0 GB—16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 4K context · ~676 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

0.6GBat 4K context

Weights
0.2 GB
KV cache
0.1 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 23.4 GB free · ~1191 tok/s

≥50 tok/s needs ≥42 GB/s · RTX 5090 ~2118, M5 Ultra ~1563

Which Hardware Can Run Lite Oute 1 300M?

Q4_K_M · 0.6 GB

Lite Oute 1 300M (Q4_K_M) requires 0.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 4K context window can add up to 0.1 GB, bringing total usage to 0.6 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run Lite Oute 1 300M, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 0.6 GB · ~322 tok/s · 4K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 0.6 GB · ~426 tok/s · 4K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 0.6 GB · ~530 tok/s · 4K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 0.6 GB · ~1191 tok/s · 4K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 0.6 GB · ~153 tok/s · 4KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 0.6 GB · ~695 tok/s · 4KMacs →

Alternatives to Lite Oute 1 300M

Similar models

1
ModelScoreVRAMtok/sWhy it is similar
T5gemma S S PrefixlmGoogle—1.7 GB~950same size

Specifications

Publisher
OuteAI
Parameters
300M
Architecture
MistralForCausalLM
Context Length
4,096 tokens
Vocabulary Size
32,768
Release Date
2024-07-28
License
Apache 2.0

Frequently Asked Questions

How much VRAM does Lite Oute 1 300M need?

Lite Oute 1 300M requires 0.6 GB of VRAM at Q4_K_M, or 1.0 GB at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 300M × 4.8 bits ÷ 8 = 0.2 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 ≈ 0.4 GB (at full 4K context)

VRAM usage by quantization

0.6 GB
0.6 GB

Learn more about VRAM estimation →

What's the best quantization for Lite Oute 1 300M?

For Lite Oute 1 300M, Q4_K_M (0.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.5 GB.

VRAM requirement by quantization

Q2_K
0.5 GB
Q4_K_M ★
0.6 GB
Q5_K_M
0.6 GB
Q6_K
0.6 GB
Q8_0
0.7 GB
BF16
1.0 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Lite Oute 1 300M on a Mac?

Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run Lite Oute 1 300M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.6 GB of usable unified memory (RAM minus macOS overhead).

Can I run Lite Oute 1 300M locally?

Yes — Lite Oute 1 300M can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Lite Oute 1 300M?

At Q4_K_M, Lite Oute 1 300M can reach ~8727 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1191 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 ÷ 0.55 × 0.65 = ~9455 tok/s

Estimated speed at Q4_K_M (0.6 GB)

~9455 tok/s
~1191 tok/s
~9455 tok/s
~8727 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 Lite Oute 1 300M?

At Q4_K_M, the download is about 0.18 GB. The full-precision BF16 version is 0.60 GB. The smallest option (Q2_K) is 0.13 GB.

Which GPUs can run Lite Oute 1 300M?

114 consumer GPUs can run Lite Oute 1 300M at Q4_K_M. Top options include AMD Radeon RX 5600 XT, AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB. 114 GPUs have plenty of headroom for comfortable inference.

Which devices can run Lite Oute 1 300M?

185 devices with unified memory can run Lite Oute 1 300M at Q4_K_M (0.6 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.