llmrun
OVHaiLLMOlalaForCausalLM

Olala v1.0 Mini 7A1B — Hardware Requirements & GPU Compatibility

ChatReasoningFunctions

Olala v1.0 Mini 7A1B is a 6.8B-parameter open language model from OVHaiLLM. It supports a context window of up to 100,000 tokens. At Q4_K_M it needs about 4.36 GB of VRAM — see which GPUs and Macs can run it below.

6.8B params · dense100K contextApache 2.01.0K downloads177 likes7.1K quant downloads
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 16KBest on24 GB Q4_K_M · ~150 tok/s · 98KMacs from8 GB Q4_K_M · ~16 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Olala v1.0 Mini 7A1B

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/OVHaiLLM/Olala-v1.0-mini-7A1B-GGUF

Q4_K_M fits fully on the RTX 4090 · 17.2 GB free · 16K context

Download: Olala-v1.0-mini-7A1B-Q4_K_M.gguf4.06 GBOVHaiLLM

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 2080 Ti (11 GB) (4 GB headroom) · Q4_K_M

Generation speed
~92 tok/s
generation speed
Cost per 1M output tokens
$0.27
per 1M output tokens

How Much VRAM Does Olala v1.0 Mini 7A1B Need?

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

QuantizationVRAM+32KOn RTX 4090 (reference)
3.2 GB8.4 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 98K context · ~206 tok/s
3.6 GB8.9 GB3-bit medium — 3-bit medium quantizationFits: 98K context · ~182 tok/s
4.4 GB9.6 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 98K context · ~150 tok/s
5.1 GB10.4 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 98K context · ~128 tok/s
5.9 GB11.1 GB6-bit, very good — 6-bit quantization, very good qualityFits: 98K context · ~111 tok/s
7.1 GB12.3 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 98K context · ~93 tok/s
13.8 GB19.1 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 32K context · ~47 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

6.8GBat 16K context

Weights
3.7 GB
KV cache
2.8 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 17.2 GB free · ~150 tok/s

≥50 tok/s needs ≥335 GB/s · RTX 5090 ~267, M5 Ultra ~197

Which Hardware Can Run Olala v1.0 Mini 7A1B?

Q4_K_M · 4.4 GB

Olala v1.0 Mini 7A1B (Q4_K_M) requires 4.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 6+ GB is recommended. 107 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce GTX 1660 SUPER. 185 devices with unified memory can run Olala v1.0 Mini 7A1B, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), MacBook Air 13" M3 (8 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 6.8 GB · ~41 tok/s · 16K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 6.8 GB · ~54 tok/s · 32K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 6.8 GB · ~67 tok/s · 64K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 6.8 GB · ~150 tok/s · 98K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 6.8 GB · ~19 tok/s · 98KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 6.8 GB · ~88 tok/s · 98KMacs →

Alternatives to Olala v1.0 Mini 7A1B

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Olmo 3 7B InstructAllen AI—8.4 GB~114same size
Mistral 7B Instruct v0.3Mistral AI—6.8 GB~133same size
CodeQwen1.5 7BAlibaba—5.7 GB~137same size
Llava 1.5 7B HFllava-hf—5 GB~141same size
Baichuan2 7B Basebaichuan-inc—5 GB~142same size
Internlm 7BInternLM—15.4 GB~43same size

Specifications

Publisher
OVHaiLLM
Parameters
6.8B
Architecture
OlalaForCausalLM
Context Length
100,000 tokens
Vocabulary Size
151,936
Release Date
2026-10-30
License
Apache 2.0

Frequently Asked Questions

How much VRAM does Olala v1.0 Mini 7A1B need?

Olala v1.0 Mini 7A1B requires 4.4 GB of VRAM at Q4_K_M, or 13.8 GB at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 6.8B × 4.8 bits ÷ 8 = 4.1 GB

KV Cache + Overhead ≈ 0.3 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 ≈ 0.3 GB (at full 100K context)

VRAM usage by quantization

4.4 GB
4.4 GB

Learn more about VRAM estimation →

What's the best quantization for Olala v1.0 Mini 7A1B?

For Olala v1.0 Mini 7A1B, Q4_K_M (4.4 GB) offers the best balance of quality and VRAM usage. Q5_K_M (5.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3.2 GB.

VRAM requirement by quantization

Q2_K
3.2 GB
Q4_K_M ★
4.4 GB
Q5_K_M
5.1 GB
Q6_K
5.9 GB
Q8_0
7.1 GB
BF16
13.8 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Olala v1.0 Mini 7A1B on a Mac?

Yes — Mac Mini M2 (8 GB) and 158 other Macs can run Olala v1.0 Mini 7A1B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.4 GB of usable unified memory (RAM minus macOS overhead).

Can I run Olala v1.0 Mini 7A1B locally?

Yes — Olala v1.0 Mini 7A1B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Olala v1.0 Mini 7A1B?

At Q4_K_M, Olala v1.0 Mini 7A1B can reach ~1101 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~150 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 ÷ 4.36 × 0.65 = ~1193 tok/s

Estimated speed at Q4_K_M (4.4 GB)

~1193 tok/s
~150 tok/s
~1193 tok/s
~1101 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 Olala v1.0 Mini 7A1B?

At Q4_K_M, the download is about 4.06 GB. The full-precision BF16 version is 13.55 GB. The smallest option (Q2_K) is 2.88 GB.

Which GPUs can run Olala v1.0 Mini 7A1B?

107 consumer GPUs can run Olala v1.0 Mini 7A1B at Q4_K_M. Top options include AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB, AMD Radeon RX 6600, AMD Radeon RX 5600 XT. 95 GPUs have plenty of headroom for comfortable inference.

Which devices can run Olala v1.0 Mini 7A1B?

185 devices with unified memory can run Olala v1.0 Mini 7A1B at Q4_K_M (4.4 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.