Can CogVLM2 19B run on AMD Instinct MI100 32GB?

YES — Runs Great

S87Excellent

Estimated from fit model

CogVLM2 19B needs ~18.1 GB VRAM. AMD Instinct MI100 32GB has 32.0 GB. With Q4_K_M quantization, expect ~74 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 18.1 GB, 74.0 tok/s, Runs well

18.1 GB required32.0 GB available

57% VRAM used

Fit status

Runs well

Decode

74.0 tok/s

TTFT

2615 ms

Safe context

Memory

18.1 GB / 32.0 GB

Memory breakdown

Weights11.6 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsCogVLM2 19B on AMD Instinct MI100 32GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.

When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.

Key benefits of running locally:
  - Full privacy: your prompts never leave your machine
  - No per-token cost or rate limits
  - Works offline once the model is downloaded
  - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:

  Model size     Q4 (4-bit)    Q8 (8-bit)    FP16
  7B params      ~4.3 GB       ~7.5 GB       ~14 GB
  13B params     ~7.9 GB       ~13.9 GB      ~26 GB
  70B params     ~42.7 GB      ~74.9 GB      ~140 GB

Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 74.0 tok/s decode · 2.6s TTFT (warm) · 185 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	74.0 tok/s	1426 ms	8K
Coding	S	Runs well	74.0 tok/s	2615 ms	8K
Agentic Coding	S	Runs well	74.0 tok/s	3804 ms	8K
Reasoning	S	Runs well	74.0 tok/s	3090 ms	8K
RAG	S	Runs well	74.0 tok/s	4755 ms	8K

Quantization options

How CogVLM2 19B (19B params) fits at each quantization level on AMD Instinct MI100 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.4 GB	Low	A78
Q3_K_S	3	9.3 GB	Low	A79
NVFP4	4	10.6 GB	Medium	A79
Q4_K_M	4	11.6 GB	Medium	A80
Q5_K_M	5	13.7 GB	High	A81
Q6_K	6	15.6 GB	High	A82
Q8_0Best for your GPU	8	20.3 GB	Very High	A82
F16	16	38.9 GB	Maximum	F0

Get started

Copy-paste commands to run CogVLM2 19B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "THUDM/cogvlm2-llama3-chat-19B" \
  --hf-file "cogvlm2-llama3-chat-19B-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your AMD Instinct MI100 32GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	120.7 tok/s
Qwen 3.5 27B	27B	S	52.3 tok/s
Qwen 3.6 27B	27B	S	32.6 tok/s
Qwen 3.6 35B A3B	35B	S	101.4 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	124.8 tok/s

Frequently asked questions

Can AMD Instinct MI100 32GB run CogVLM2 19B?

Yes, AMD Instinct MI100 32GB can run CogVLM2 19B with a S grade (Runs well). Expected decode speed: 74.0 tok/s.

How much VRAM does CogVLM2 19B need?

CogVLM2 19B (19B parameters) requires approximately 18.1 GB of memory with Q4_K_M quantization.

What is the best quantization for CogVLM2 19B?

The recommended quantization for CogVLM2 19B is Q4_K_M, which balances quality and memory efficiency.

What speed will CogVLM2 19B run at on AMD Instinct MI100 32GB?

On AMD Instinct MI100 32GB, CogVLM2 19B achieves approximately 74.0 tokens per second decode speed with a time-to-first-token of 2615ms using Q4_K_M quantization.

Can AMD Instinct MI100 32GB run CogVLM2 19B for coding?

For coding workloads, CogVLM2 19B on AMD Instinct MI100 32GB receives a S grade with 74.0 tok/s and 8K context.

What context window can CogVLM2 19B use on AMD Instinct MI100 32GB?

On AMD Instinct MI100 32GB, CogVLM2 19B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI100 32GB See all hardware for CogVLM2 19B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/cogvlm2-19b-on-instinct-mi100-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: