Midnight Miqu 70B v1.0 — Hardware Requirements & GPU Compatibility
Chat
Midnight Miqu 70B v1.0 is a 69.0B-parameter open language model from sophosympatheia. It supports a context window of up to 32,764 tokens. At Q4_K_M it needs about 42.36 GB of VRAM — see which GPUs and Macs can run it below.
Midnight Miqu 70B v1.0 runs on a 48 GB+ Mac or a workstation GPU
Best local pick → Mac Studio M5 Max (48 GB) · Q4_K_M · 47.1 GB · ~10 tok/s
Macs from 48 GB (Q4_K_M · ~10 tok/s)
Other
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Midnight Miqu 70B v1.0
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve sophosympatheia/Midnight-Miqu-70B-v1.0 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on A100 80GB (32 GB headroom) · Q4_K_M
- Generation speed
- ~31 tok/s
- generation speed
- Cost per 1M output tokens
- $10.27
- per 1M output tokens
How Much VRAM Does Midnight Miqu 70B v1.0 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 30.3 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Does not fit: needs 35 GB | |
| 34.6 GB | — | 3-bit medium — 3-bit medium quantization | Does not fit: needs 39.3 GB | |
| 42.4 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Does not fit: needs 47.1 GB | |
| 50.1 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 54.8 GB | |
| 57.9 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 62.6 GB | |
| 70.0 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 74.7 GB | |
| 138.9 GB | — | 16-bit · full — Full half-precision — baseline for inference | Does not fit: needs 143.6 GB |
Selected Q4_K_M
4-bit medium quantization47.1GBat 16K context
- Weights
- 41.4 GB
- KV cache
- 5.4 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 23.1 GB more
Which Hardware Can Run Midnight Miqu 70B v1.0?
Q4_K_M · 42.4 GBMidnight Miqu 70B v1.0 (Q4_K_M) requires 42.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 56+ GB is recommended. Using the full 33K context window can add up to 10.1 GB, bringing total usage to 52.4 GB. No consumer GPU has enough memory. 67 devices with unified memory can run Midnight Miqu 70B v1.0, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Pro M2 Ultra (64 GB).
48 GB
48 GB tier →fits · 0.9 GB free · up to 16K ctx
2 Mac classes · 1 device family
M5 Max48 GB~10Simulate output on Mac Studio M5 Max (48 GB)M5 Pro48 GB~5Simulate output on Mac Mini M5 Pro (48 GB)Snapdragon X2 Elite Extreme (X2E-96-100)~4Simulate output on Snapdragon X2 Elite Extreme Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Llama 3.3 70B InstructMeta | 79.7 | 51.3 GB | —needs > 24 GB | same size |
| Qwen2.5 VL 72B InstructAlibaba | — | 49.7 GB | —needs > 24 GB | same size |
| Qwen2 VL 72B InstructAlibaba | — | 49.7 GB | —needs > 24 GB | same size |
| Qwen1.5 72B ChatAlibaba | — | 86.6 GB | —needs > 24 GB | same size |
| CodeLlama 70B Instruct HFMeta | — | 23.2 GB | ~29 | same size |
| Apertus 70B 2509swiss-ai | — | 48 GB | —needs > 24 GB | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- sophosympatheia
- Parameters
- 69.0B
- Architecture
- LlamaForCausalLM
- Context Length
- 32,764 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2024-02-29
- License
- Other
Frequently Asked Questions
How much VRAM does Midnight Miqu 70B v1.0 need?
Midnight Miqu 70B v1.0 requires 42.4 GB of VRAM at Q4_K_M, or 138.9 GB at FP16. Full 33K context adds up to 10.1 GB (52.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 69.0B × 4.8 bits ÷ 8 = 41.4 GB
KV Cache + Overhead ≈ 1 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 ≈ 11 GB (at full 33K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Midnight Miqu 70B v1.0?
Yes, at Q2_K (30.3 GB) or lower. Higher quantizations like Q3_K_M (34.6 GB) exceed the NVIDIA GeForce RTX 5090's 32 GB.
What's the best quantization for Midnight Miqu 70B v1.0?
For Midnight Miqu 70B v1.0, Q4_K_M (42.4 GB) offers the best balance of quality and VRAM usage. Q5_K_M (50.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 30.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Midnight Miqu 70B v1.0 on a Mac?
Yes — Mac Studio M5 Max (48 GB) and 55 other Macs can run Midnight Miqu 70B v1.0. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 42.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run Midnight Miqu 70B v1.0 locally?
Yes — Midnight Miqu 70B v1.0 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Midnight Miqu 70B v1.0?
At Q4_K_M, Midnight Miqu 70B v1.0 can reach ~113 tok/s on AMD Instinct MI350X. 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 ÷ 42.4 × 0.65 = ~123 tok/s
Estimated speed at Q4_K_M (42.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Midnight Miqu 70B v1.0?
At Q4_K_M, the download is about 41.39 GB. The full-precision FP16 version is 137.95 GB. The smallest option (Q2_K) is 29.32 GB.
Which GPUs can run Midnight Miqu 70B v1.0?
No single consumer GPU has enough VRAM to run Midnight Miqu 70B v1.0 at Q4_K_M (42.4 GB). Multi-GPU or professional hardware is required.
Which devices can run Midnight Miqu 70B v1.0?
67 devices with unified memory can run Midnight Miqu 70B v1.0 at Q4_K_M (42.4 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.