Midm 2.0 Mini Instruct — Hardware Requirements & GPU Compatibility
ChatFunctions
Midm 2.0 Mini Instruct is a 2.3B-parameter open language model from K-intelligence. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 1.86 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 · 32K)Best on 24 GB (Q4_K_M · ~352 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~39 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Midm 2.0 Mini Instruct
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 serve K-intelligence/Midm-2.0-Mini-Instruct --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3060 12GB (8 GB headroom) · Q4_K_M
- Generation speed
- ~126 tok/s
- generation speed
- Cost per 1M output tokens
- $0.14
- per 1M output tokens
How Much VRAM Does Midm 2.0 Mini Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.5 GB | 4.1 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~449 tok/s | |
| 1.6 GB | 4.2 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~410 tok/s | |
| 1.9 GB | 4.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~352 tok/s | |
| 2.1 GB | 4.8 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~309 tok/s | |
| 2.4 GB | 5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~275 tok/s | |
| 2.8 GB | 5.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~236 tok/s | |
| 5.1 GB | 7.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~129 tok/s |
Selected Q4_K_M
4-bit medium quantization3.1GBat 16K context
- Weights
- 1.4 GB
- KV cache
- 1.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.9 GB free · ~352 tok/s
≥50 tok/s needs ≥143 GB/s · RTX 5090 ~626, RTX 3090 Ti ~352
Which Hardware Can Run Midm 2.0 Mini Instruct?
Q4_K_M · 1.9 GBMidm 2.0 Mini Instruct (Q4_K_M) requires 1.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 33K context window can add up to 2.6 GB, bringing total usage to 4.5 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Midm 2.0 Mini Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.9 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~266Simulate output on RTX 3080RTX 2080 Ti~215Simulate output on RTX 2080 TiRTX 3070 Ti~213Simulate output on RTX 3070 TiM3*8 GB~39Simulate output on iMac 24" M3 (8 GB)Orin Nano~36Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~26Simulate output on iPhone 1720 GB
fits · 16.9 GB free · up to 32K ctx
1 GPU
RX 7900 XT~258Simulate output on RX 7900 XT32–40 GB
fits · 28.9 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~626Simulate output on RTX 5090M5 Max36 GB~173Simulate output on Mac Studio M5 Max (36 GB)M532 GB~58Simulate output on MacBook Air 13" M5 (32 GB)Orin~72Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~47Simulate output on Snapdragon X Elite 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 |
|---|---|---|---|---|
| LFM3 Omni 2BLiquid AI | — | 2.4 GB | ~385 | same size |
| North Micro Vision InstructCohere | — | 7.1 GB | ~119 | same size |
| Qwen3.5 2BAlibaba | — | 1.9 GB | ~370 | same size |
| Qwen2 VL 2B InstructAlibaba | — | 2.1 GB | ~390 | same size |
| Kimi K3 DSparkRadixArk | — | 2.2 GB | ~381 | same size |
| EXAONE 3.5 2.4B InstructLGAI-EXAONE | — | 3.4 GB | ~412 | same size |
Specifications
- Publisher
- K-intelligence
- Parameters
- 2.3B
- Architecture
- LlamaForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 131,392
- Release Date
- 2025-07-03
- License
- MIT
Frequently Asked Questions
How much VRAM does Midm 2.0 Mini Instruct need?
Midm 2.0 Mini Instruct requires 1.9 GB of VRAM at Q4_K_M, or 5.1 GB at BF16. Full 33K context adds up to 2.6 GB (4.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.3B × 4.8 bits ÷ 8 = 1.4 GB
KV Cache + Overhead ≈ 0.5 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 ≈ 3.1 GB (at full 33K context)
VRAM usage by quantization
What's the best quantization for Midm 2.0 Mini Instruct?
For Midm 2.0 Mini Instruct, Q4_K_M (1.9 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Midm 2.0 Mini Instruct on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Midm 2.0 Mini Instruct. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Midm 2.0 Mini Instruct locally?
Yes — Midm 2.0 Mini Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Midm 2.0 Mini Instruct?
At Q4_K_M, Midm 2.0 Mini Instruct can reach ~2581 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~352 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 ÷ 1.86 × 0.65 = ~2796 tok/s
Estimated speed at Q4_K_M (1.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Midm 2.0 Mini Instruct?
At Q4_K_M, the download is about 1.38 GB. The full-precision BF16 version is 4.61 GB. The smallest option (Q2_K) is 0.98 GB.
Which GPUs can run Midm 2.0 Mini Instruct?
52 consumer GPUs can run Midm 2.0 Mini Instruct at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Midm 2.0 Mini Instruct?
163 devices with unified memory can run Midm 2.0 Mini Instruct at Q4_K_M (1.9 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.