Olala v1.0 Mini 7A1B — Hardware Requirements & GPU Compatibility
ChatReasoningFunctionsOlala 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.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~150 tok/s · 98K)Macs from 8 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 run hf.co/OVHaiLLM/Olala-v1.0-mini-7A1B-GGUFQ4_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
Ways to runOther ways
each opens step-by-stepRun 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.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.2 GB | 8.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 98K context · ~206 tok/s | |
| 3.6 GB | 8.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 98K context · ~182 tok/s | |
| 4.4 GB | 9.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 98K context · ~150 tok/s | |
| 5.1 GB | 10.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 98K context · ~128 tok/s | |
| 5.9 GB | 11.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 98K context · ~111 tok/s | |
| 7.1 GB | 12.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 98K context · ~93 tok/s | |
| 13.8 GB | 19.1 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~47 tok/s |
Selected Q4_K_M
4-bit medium quantization6.8GBat 16K context
- Weights
- 3.7 GB
- KV cache
- 2.8 GB
- Overhead
- 0.3 GB
Which Hardware Can Run Olala v1.0 Mini 7A1B?
Q4_K_M · 4.4 GBOlala 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).
12 GB
12 GB tier →fits · 5.2 GB free · up to 32K ctx
16 GPUs · 1 device family
RTX 3080 12GB~136Simulate output on RTX 3080 12GBRTX 3080 Ti~136Simulate output on RTX 3080 TiRTX 5070~100Simulate output on RTX 5070iPhone~12Simulate output on Apple iPhone 17 Pro20 GB
fits · 13.2 GB free · up to 64K ctx
1 GPU
RX 7900 XT~110Simulate output on RX 7900 XT32–40 GB
fits · 25.2 GB free · up to 98K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~267Simulate output on RTX 5090M5 Max*36 GB~74Simulate output on Mac Studio M5 Max (36 GB)M632 GB~27Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~45Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~31Simulate output on NVIDIA Jetson AGX Orin 32GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Olmo 3 7B InstructAllen AI | — | 8.4 GB | ~114 | same size |
| Mistral 7B Instruct v0.3Mistral AI | — | 6.8 GB | ~133 | same size |
| CodeQwen1.5 7BAlibaba | — | 5.7 GB | ~137 | same size |
| Llava 1.5 7B HFllava-hf | — | 5 GB | ~141 | same size |
| Baichuan2 7B Basebaichuan-inc | — | 5 GB | ~142 | same size |
| Internlm 7BInternLM | — | 15.4 GB | ~43 | same 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
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
★ Recommended — best balance of quality and VRAM usage.
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)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
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.