InternVL3.5 241B-A28B on AMD Instinct MI350X

Can the AMD Instinct MI350X run InternVL3.5 241B-A28B?

Yes, it runs great

Runs great. At Q6_K it needs about 214 GB of 288 GB usable, with an estimated speed of 119 tok/s.

Best quant: Q6_K
Generation speed: 119 tok/s
Prompt processing: 3,034 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 40K

Best app to run it on the AMD Instinct MI350X

On Linux

vLLM

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve OpenGVLab/InternVL3_5-241B-A28B

Lemonade AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.
LM Studio Point-and-click: search, download and chat in one window.

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull mradermacher/InternVL3_5-241B-A28B-GGUF:Q6_K

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download InternVL3.5 241B-A28B

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/mradermacher/InternVL3_5-241B-A28B-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/InternVL3_5-241B-A28B-GGUF

Original weights · Hugging Face

Full-precision files from Shanghai AI Lab, for fine-tuning, vLLM, Transformers.

huggingface.co/OpenGVLab/InternVL3_5-241B-A28B (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q6_K, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the AMD Instinct MI350X: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	38.3 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	93.3 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the AMD Instinct MI350X

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	113 GB	288 GB	195 tok/s	Runs great	60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	135 GB	288 GB	172 tok/s	Runs great	72Great quality (A) · 72 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	163 GB	288 GB	150 tok/s	Runs great	81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q5_K_M`	187 GB	288 GB	133 tok/s	Runs great	83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	214 GB	288 GB	119 tok/s	Runs great	85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	272 GB	288 GB	97.0 tok/s	Runs welltight fit	86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`F16`	498 GB	288 GB	—	Won't run	86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q4_K_M · 28.0 tok/s · Runs well (tight fit)
72Great quality (A) · 72 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q3_K_M · 34.7 tok/s · Runs well (tight fit)
81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q4_K_M · 28.0 tok/s · Runs well
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) Q2_K · 18.5 tok/s · Runs well (tight fit)
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q2_K · 38.5 tok/s · Runs well (offloads to RAM)
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) Q2_K · 17.2 tok/s · Runs well (over GPU memory limit)

Quick answers

How much memory does InternVL3.5 241B-A28B need on the AMD Instinct MI350X 288GB?

At Q6_K it needs about 214 GB. The AMD Instinct MI350X 288GB has 288 GB usable.

How fast is InternVL3.5 241B-A28B on the AMD Instinct MI350X 288GB?

About 119 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of InternVL3.5 241B-A28B should I use on the AMD Instinct MI350X 288GB?

Q6_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.