VOOZH about

URL: https://willitrunai.com/can-run/command-r-35b-on-instinct-mi60-32gb

⇱ Command R 35B on AMD Instinct MI60 32GB? TIGHT FIT

Can Command R 35B run on AMD Instinct MI60 32GB?

YES — Tight Fit

A76Great
○Estimated from fit model

Command R 35B needs ~27.9 GB VRAM. AMD Instinct MI60 32GB has 32.0 GB. With Q4_K_M quantization, expect ~26 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: HighStack: StandardBottleneck: Balanced
Share:

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) — 27.9 GB, 25.6 tok/s, Tight fit
27.9 GB required32.0 GB available
87% VRAM used

Fit status

Tight fit

Decode

25.6 tok/s

TTFT

7575 ms

Safe context

43K

Memory

27.9 GB / 32.0 GB

Memory breakdown

Weights21.3 GB
KV Cache2.4 GB
Runtime0.9 GB
Headroom3.2 GB

See how fast it feels

See how fast it feelsCommand R 35B on AMD Instinct MI60 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: 25.6 tok/s decode · 7.6s TTFT (warm) · 64 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

WorkloadGradeFitDecodeTTFTContext
ChatATight fit25.6 tok/s4132 ms43K
CodingATight fit25.6 tok/s7575 ms43K
Agentic CodingATight fit25.6 tok/s11018 ms43K
ReasoningATight fit25.6 tok/s8952 ms43K
RAGATight fit25.6 tok/s13773 ms43K

Quantization options

How Command R 35B (35B params) fits at each quantization level on AMD Instinct MI60 32GB (32.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
13.7 GB
LowA75
Q3_K_S
3
17.2 GB
LowA76
NVFP4
4
19.6 GB
MediumA75
Q4_K_M
4
21.3 GB
MediumA75
Q5_K_MBest for your GPU
5
25.2 GB
HighA75
Q6_K
6
28.7 GB
HighF0
Q8_0
8
37.5 GB
Very HighF0
F16
16
71.8 GB
MaximumF0

Get started

Copy-paste commands to run Command R 35B on your machine.

Run

ollama run command-r

Your hardware

More models your AMD Instinct MI60 32GB can run

ModelParamsGradeDecodeCapabilities
👁 Moonshot AI
Kimi Linear 48B A3B		48BB11.1 tok/s

Frequently asked questions

See all results for AMD Instinct MI60 32GBSee all hardware for Command R 35B