Qwen3.5 Medical Ft — Hardware Requirements & GPU Compatibility
Chat
Qwen3.5 Medical Ft is a 9.7B-parameter open language model from vadimbelsky in the Qwen 3.5 family. It supports a context window of up to 262,144 tokens. At BF16 it needs about 19.87 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs on 24 GB (BF16 · ~33 tok/s · 128K)Macs from 24 GB (BF16 · ~11 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen3.5 Medical Ft
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 vadimbelsky/qwen3.5-medical-ft --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 5090 (32 GB) (11 GB headroom) · BF16
- Generation speed
- ~59 tok/s
- generation speed
- Cost per 1M output tokens
- $2.36
- per 1M output tokens
How Much VRAM Does Qwen3.5 Medical Ft Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 19.9 GB | 20.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~33 tok/s |
Selected BF16
Brain floating point 1620.1GBat 16K context
- Weights
- 19.3 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 3.9 GB free · ~33 tok/s
≥50 tok/s needs ≥1.53 TB/s · RTX 5090 ~59
Which Hardware Can Run Qwen3.5 Medical Ft?
BF16 · 19.9 GBQwen3.5 Medical Ft (BF16) requires 19.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ GB is recommended. Using the full 262K context window can add up to 8.3 GB, bringing total usage to 28.2 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Qwen3.5 Medical Ft, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
tight · up to 8K ctx
1 GPU
RX 7900 XT~24Simulate output on RX 7900 XT32–40 GB
fits · 11.9 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~59Simulate output on RTX 5090M5 Max36 GB~16Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to Qwen3.5 Medical Ft
Qwen 3.5 family · 34 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| SenseNova Loop 9B Previewsensenova | — | 8.2 GB | ~103 | same size |
| ZDTaichu5.0 9BTaichuAI | — | 9.2 GB | ~101 | same size |
| Ornith 1.5 9Bornith-ai | — | 6.6 GB | ~103 | same size |
| ZAYA1 VL 8BZyphra | — | 7.5 GB | ~346 | same size |
| Qwopus3.5 9B v3Jackrong | — | 6.6 GB | ~103 | same size |
| MiniCPM O 4 5OpenBMB | — | 8.3 GB | ~105 | same size |
Specifications
- Publisher
- vadimbelsky
- Family
- Qwen 3.5
- Parameters
- 9.7B
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-03-15
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3.5 Medical Ft need?
Qwen3.5 Medical Ft requires 19.9 GB of VRAM at BF16. Full 262K context adds up to 8.3 GB (28.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 9.7B × 16 bits ÷ 8 = 19.3 GB
KV Cache + Overhead ≈ 0.6 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 ≈ 8.9 GB (at full 262K context)
VRAM usage by quantization
Can I run Qwen3.5 Medical Ft on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Qwen3.5 Medical Ft. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 19.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Qwen3.5 Medical Ft locally?
Yes — Qwen3.5 Medical Ft can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3.5 Medical Ft?
At BF16, Qwen3.5 Medical Ft can reach ~242 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~33 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 ÷ 19.87 × 0.65 = ~262 tok/s
Estimated speed at BF16 (19.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen3.5 Medical Ft?
At BF16, the download is about 19.31 GB.
Which GPUs can run Qwen3.5 Medical Ft?
8 consumer GPUs can run Qwen3.5 Medical Ft at BF16. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Qwen3.5 Medical Ft?
122 devices with unified memory can run Qwen3.5 Medical Ft at BF16 (19.9 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.