MedPsy 4B — Hardware Requirements & GPU Compatibility
Chat
MedPsy 4B is a 4.4B-parameter open language model from qvac. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 3.14 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 · ~209 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~23 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run MedPsy 4B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve qvac/MedPsy-4B --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 RTX 3060 12GB (7 GB headroom) · Q4_K_M
- Generation speed
- ~75 tok/s
- generation speed
- Cost per 1M output tokens
- $0.31
- per 1M output tokens
How Much VRAM Does MedPsy 4B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.4 GB | 5.2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~278 tok/s | |
| 2.6 GB | 5.5 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~248 tok/s | |
| 3.1 GB | 6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~209 tok/s | |
| 3.6 GB | 6.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~181 tok/s | |
| 4.1 GB | 7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~159 tok/s | |
| 4.9 GB | 7.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~134 tok/s | |
| 9.3 GB | 12.1 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~70 tok/s |
Selected Q4_K_M
4-bit medium quantization4.5GBat 16K context
- Weights
- 2.7 GB
- KV cache
- 1.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.5 GB free · ~209 tok/s
≥50 tok/s needs ≥241 GB/s · RTX 5090 ~371, RTX 3090 Ti ~209
Which Hardware Can Run MedPsy 4B?
Q4_K_M · 3.1 GBMedPsy 4B (Q4_K_M) requires 3.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ GB is recommended. Using the full 262K context window can add up to 24.0 GB, bringing total usage to 27.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run MedPsy 4B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.5 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~157Simulate output on RTX 3080RTX 2080 Ti~128Simulate output on RTX 2080 TiRTX 3070 Ti~126Simulate output on RTX 3070 TiM3*8 GB~23Simulate output on iMac 24" M3 (8 GB)Orin Nano~21Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~15Simulate output on iPhone 1720 GB
fits · 15.5 GB free · up to 128K ctx
1 GPU
RX 7900 XT~153Simulate output on RX 7900 XT32–40 GB
fits · 27.5 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~371Simulate output on RTX 5090M5 Max36 GB~103Simulate output on Mac Studio M5 Max (36 GB)M532 GB~34Simulate output on MacBook Air 13" M5 (32 GB)Orin~42Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~28Simulate 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 |
|---|---|---|---|---|
| Gemma 3 4B ITGoogle | 64.0 | 5 GB | ~231 | same size |
| Qwen3.5 4BAlibaba | — | 3.4 GB | ~201 | same size |
| Qwen3 VL 4B InstructAlibaba | — | 4.5 GB | ~208 | same size |
| Phi 3.5 Vision InstructMicrosoft | — | 9.2 GB | ~183 | same size |
| Agents A1 4BInternScience | — | 3.4 GB | ~205 | same size |
| Qwen3.6 27B MTPLX Optimized SpeedYoussofal | — | 4 GB | ~185 | same size |
Specifications
- Publisher
- qvac
- Parameters
- 4.4B
- Architecture
- Qwen3ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-04-28
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does MedPsy 4B need?
MedPsy 4B requires 3.1 GB of VRAM at Q4_K_M, or 9.3 GB at BF16. Full 262K context adds up to 24.0 GB (27.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 4.4B × 4.8 bits ÷ 8 = 2.6 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 ≈ 24.5 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for MedPsy 4B?
For MedPsy 4B, Q4_K_M (3.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (3.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run MedPsy 4B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run MedPsy 4B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 3.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run MedPsy 4B locally?
Yes — MedPsy 4B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is MedPsy 4B?
At Q4_K_M, MedPsy 4B can reach ~1529 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~209 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 ÷ 3.14 × 0.65 = ~1656 tok/s
Estimated speed at Q4_K_M (3.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of MedPsy 4B?
At Q4_K_M, the download is about 2.65 GB. The full-precision BF16 version is 8.82 GB. The smallest option (Q2_K) is 1.87 GB.
Which GPUs can run MedPsy 4B?
52 consumer GPUs can run MedPsy 4B 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 MedPsy 4B?
163 devices with unified memory can run MedPsy 4B at Q4_K_M (3.1 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.