Reference estimate · Ollama

What fits this hardware configuration?

Start with memory fit, then check the model's task and setup instructions. A verdict estimates compatibility; it does not measure answer quality or speed.

Hardware and operating systemSystem / unified memoryContext length

Ollama reference estimate. No download or scan needed. Desktop GPU capacities are reference specifications; this form does not detect your computer.

Scenario assumptions

Illustrative 8-core CPU and 500 GB free disk, so these estimates do not check your actual CPU or storage. Available RAM, GPU budget, free VRAM and driver version are unknown. The engine applies memory reserves. GPU paths assume a working supported driver/backend; runtime-version compatibility is not checked. Apple memory is one shared pool. One GPU is evaluated; memory is not pooled across cards.

This configuration is not saved as your PC, and does not add to the completed-scan counter.

Four builds to compare by task

Editorial examples chosen for their documented tasks, all Q4_K_M at 4,096 tokens. Check the verdict before downloading. These are estimates, not benchmark rankings.

Short conversations and summaries

llama3.2:3b

A small instruction-tuned model for trying local chat with more memory headroom. Review summaries against the source text.

Task and build source · Catalog checked 2026-10-13

Excellent fit

Est. memory 2.9 GB · medium confidence

Model fully fits in usable GPU VRAM.

ollama run llama3.2:3b

General instruction following

llama3.1:8b

An 8B instruction-tuned alternative to compare on your own prompts. It needs more memory than the 3B example and can still give incorrect answers.

Task and build source · Catalog checked 2026-10-13

Excellent fit

Est. memory 5.8 GB · medium confidence

Model fully fits in usable GPU VRAM.

ollama run llama3.1:8b

Code explanation and editing

qwen2.5-coder:7b

A code-focused instruct build. Review generated changes and run your tests; a memory fit is not evidence that its code is correct.

Task and build source · Catalog checked 2026-10-13

Excellent fit

Est. memory 5.3 GB · medium confidence

Model fully fits in usable GPU VRAM.

ollama run qwen2.5-coder:7b

A larger general-purpose comparison

qwen2.5:14b

A 14B instruct build for comparing answers when memory allows. Larger size does not establish better results for every task.

Task and build source · Catalog checked 2026-10-13

Runs with trade-offs

Est. memory 10.2 GB · medium confidence

Estimated 69% of layers offloaded to GPU (33/48); model does not fully fit in VRAM.

ollama run qwen2.5:14b

After opening Ollama's prompt, enter /set parameter num_ctx 4096 to match this calculation, within the model's supported maximum. Install a current Ollama release that supports the build. Setup and troubleshooting.

Linux · Radeon RX 7600 · 8 GB

32 GB system/unified memory · 4,096 token context · 158 good/excellent fits from 225 catalog defaults.

Showing up to 20 builds, fits first and smallest memory first. These technical defaults include base and embedding models. They are not a recommendation ranking. A model's documented maximum context still applies.

Model / exact build	Download	Est. memory	Result on this example PC
snowflake-arctic-embed snowflake-arctic-embed:22m Est. memory: 0.6 GB Download: 0.0 GB	0.0 GB	0.6 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 44 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
all-minilm all-minilm:22m Est. memory: 0.6 GB Download: 0.0 GB	0.0 GB	0.6 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 44 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
granite-embedding granite-embedding:30m Est. memory: 0.6 GB Download: 0.1 GB	0.1 GB	0.6 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 60 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
smollm smollm:135m-base-v0.2-q4_K_M Exceeds documented context maximum (2,048). Memory estimate only. Est. memory: 0.7 GB Download: 0.1 GB	0.1 GB	0.7 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 101 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
smollm2 smollm2:135m-instruct-q4_K_M Est. memory: 0.7 GB Download: 0.1 GB	0.1 GB	0.7 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 101 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
embeddinggemma embeddinggemma:300m-qat-q4_0 Exceeds documented context maximum (2,048). Memory estimate only. Est. memory: 0.8 GB Download: 0.2 GB	0.2 GB	0.8 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 227 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
functiongemma functiongemma:270m Est. memory: 0.9 GB Download: 0.3 GB	0.3 GB	0.9 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 287 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
nomic-embed-text nomic-embed-text:137m-v1.5-fp16 Exceeds documented context maximum (2,048). Memory estimate only. Est. memory: 0.9 GB Download: 0.3 GB	0.3 GB	0.9 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 262 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
qwen2 qwen2:0.5b-instruct-q4_K_M Est. memory: 0.9 GB Download: 0.4 GB	0.4 GB	0.9 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 379 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
reader-lm reader-lm:0.5b-q4_K_M Est. memory: 0.9 GB Download: 0.4 GB	0.4 GB	0.9 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 379 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
qwen2.5 qwen2.5:0.5b-base-q4_K_M Est. memory: 0.9 GB Download: 0.4 GB	0.4 GB	0.9 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 379 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
qwen2.5-coder qwen2.5-coder:0.5b-base-q4_K_M Est. memory: 0.9 GB Download: 0.4 GB	0.4 GB	0.9 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 379 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
paraphrase-multilingual paraphrase-multilingual:278m Est. memory: 1.0 GB Download: 0.5 GB	0.5 GB	1.0 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 537 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
mxbai-embed-large mxbai-embed-large:335m Est. memory: 1.1 GB Download: 0.6 GB	0.6 GB	1.1 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 639 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
bge-large bge-large:335m Est. memory: 1.1 GB Download: 0.6 GB	0.6 GB	1.1 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 639 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
minicpm-v4.6 minicpm-v4.6:1b Est. memory: 1.2 GB Download: 1.5 GB	1.5 GB	1.2 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 1.5 GB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
tinydolphin tinydolphin:1.1b-v2.8-q4_K_M Est. memory: 1.2 GB Download: 0.6 GB	0.6 GB	1.2 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 637 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
tinyllama tinyllama:1.1b-chat-v0.6-q4_K_M Exceeds documented context maximum (2,048). Memory estimate only. Est. memory: 1.2 GB Download: 0.6 GB	0.6 GB	1.2 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 638 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
qwen qwen:0.5b-text-v1.5-q4_K_M Est. memory: 1.3 GB Download: 0.4 GB	0.4 GB	1.3 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 388 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.
sailor2 sailor2:1b-chat-q4_K_M Est. memory: 1.3 GB Download: 0.7 GB	0.7 GB	1.3 GB	Excellent fit medium confidence
How this result was calculated GPU memory: Pass Model fully fits in usable GPU VRAM. System RAM: Pass Entire model runs from VRAM; no offload to system RAM required. Storage: Pass 500.0 GB free, 704 MB required. Acceleration: Pass rocm acceleration available. Assumptions and missing information This GPU and OS are on the Ollama ROCm support list. The required ROCm 7 / HIP7 driver stack has not been version-verified; an installed library alone does not prove runtime compatibility. This is a hypothetical PC. No inference benchmark was run. GB uses 1,024³ bytes. Memory includes weights, context cache and runtime overhead.

Choose a specific model and build Scan my actual hardware Install and run Ollama

Scenario assumptions

Four builds to compare by task

Short conversations and summaries

General instruction following

Code explanation and editing

A larger general-purpose comparison

Linux · Radeon RX 7600 · 8 GB

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated

How this result was calculated