What can AMD Radeon RX 7900 XTX run for long context?

Build: AMD Radeon RX 7900 XTX + — + 32 GB RAM (windows)

Memory: 24 GB VRAM + 32 GB system RAM
Runner: llama.cpp (Vulkan)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
143 models

Ranked by fit for long context use case + predicted speed. Click a row for VRAM breakdown.

#1Ministral 3B Instruct
3B
mistral
Quant: Q4_K_MContext: 8,192VRAM: 4.5 GBHeadroom: 19.5 GBTTFT: instant
239
tok/s
Estimated
Weights
1.90 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~63 ms (instant)
Model details →
#2Phi-3.5 Mini Instruct
3.8B
phi
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 7.2 GBHeadroom: 16.8 GBTTFT: instant
ollama run phi3.5:3.8b
107
tok/s
Estimated
Weights
4.10 GB
KV cache
1.90 GB
Activations
0.21 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~79 ms (instant)
Model details →
#3Falcon Mamba 7B
7B
falcon
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 8.9 GBHeadroom: 15.1 GBTTFT: fast
102
tok/s
Estimated
Weights
4.20 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Model details →
#4Codestral Mamba 7B
7B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 8.9 GBHeadroom: 15.1 GBTTFT: fast
102
tok/s
Estimated
Weights
4.20 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Model details →
#5Gemma 4 E4B (Effective 4B)
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 7.6 GBHeadroom: 16.4 GBTTFT: instant
ollama run gemma4:e4b
102
tok/s
Estimated
Weights
4.40 GB
KV cache
2.00 GB
Activations
0.23 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~83 ms (instant)
Model details →
#6Command R7B (12-2024)
8B
command-r
Quant: Q4_K_MContext: 8,192VRAM: 9.6 GBHeadroom: 14.4 GBTTFT: fast
89
tok/s
Estimated
Weights
4.40 GB
KV cache
4.00 GB
Activations
0.23 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Model details →
#7Ministral 8B Instruct
8B
mistral
Quant: Q4_K_MContext: 8,192VRAM: 10.3 GBHeadroom: 13.7 GBTTFT: fast
89
tok/s
Estimated
Weights
5.00 GB
KV cache
4.00 GB
Activations
0.26 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Model details →
#8Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.0 GBHeadroom: 14.0 GBTTFT: fast
ollama run qwen2.5:7b
58
tok/s
Estimated
Weights
8.10 GB
KV cache
0.47 GB
Activations
0.41 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Model details →
#9Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 16.8 GBHeadroom: 7.2 GBTTFT: fast
ollama run qwen3:14b
51
tok/s
Estimated
Weights
8.40 GB
KV cache
7.00 GB
Activations
0.43 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~292 ms (fast)
Model details →
#10Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 13.6 GBHeadroom: 10.4 GBTTFT: fast
ollama run qwen3:8b
51
tok/s
Estimated
Weights
8.20 GB
KV cache
4.00 GB
Activations
0.42 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~167 ms (fast)
Model details →
#11InternLM 2.5 7B Chat
7B
internlm
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.1 GBHeadroom: 14.9 GBTTFT: fast
102
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Model details →
#12Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 19.0 GBHeadroom: 5.0 GBTTFT: fast
ollama run qwen2.5:14b
45
tok/s
Estimated
Weights
10.50 GB
KV cache
7.00 GB
Activations
0.53 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~292 ms (fast)
Model details →

Runs with tradeoffs
56 models

Tight VRAM, partial CPU offload, or context-limited.

Nemotron 3 Nano (30B-A3B)
30B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 23.7 GBHeadroom: 0.3 GBTTFT: noticeable
  • • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run nemotron3:nano
24
tok/s
Estimated
Weights
18.00 GB
KV cache
3.75 GB
Activations
0.90 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~625 ms (noticeable)
Model details →
Jamba 1.5 Mini
52B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 39.0 GBHeadroom: 4.2 GBTTFT: fast
  • • Partial CPU offload: ~38% of layers run on CPU
60
tok/s
Estimated
Weights
30.00 GB
KV cache
6.50 GB
Activations
1.50 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~250 ms (fast)
Model details →
Mistral Nemo 12B Instruct
12B
mistral
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 20.7 GBHeadroom: 3.3 GBTTFT: fast
  • • Tight VRAM fit — only 3.3 GB headroom left for context growth
ollama run mistral-nemo:12b
34
tok/s
Estimated
Weights
13.00 GB
KV cache
6.00 GB
Activations
0.66 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~250 ms (fast)
Model details →
Gemma 3 27B
27B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 21.2 GBHeadroom: 2.8 GBTTFT: noticeable
  • • Tight VRAM fit — only 2.8 GB headroom left for context growth
ollama run gemma3:27b
27
tok/s
Estimated
Weights
16.00 GB
KV cache
3.38 GB
Activations
0.80 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~563 ms (noticeable)
Model details →
Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 23.7 GBHeadroom: 0.3 GBTTFT: noticeable
  • • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run qwen3:30b
24
tok/s
Estimated
Weights
18.00 GB
KV cache
3.75 GB
Activations
0.90 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~625 ms (noticeable)
Model details →
Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 23.8 GBHeadroom: 0.2 GBTTFT: noticeable
  • • Tight VRAM fit — only 0.2 GB headroom left for context growth
ollama run gemma4:31b
23
tok/s
Estimated
Weights
18.00 GB
KV cache
3.88 GB
Activations
0.90 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~646 ms (noticeable)
Model details →
Qwen 2.5 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 37.0 GBHeadroom: 6.2 GBTTFT: noticeable
  • • Partial CPU offload: ~35% of layers run on CPU
ollama run qwen2.5:32b
22
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~667 ms (noticeable)
Model details →
Command R 35B
35B
command-r
Quant: Q4_K_MContext: 8,192VRAM: 40.6 GBHeadroom: 2.6 GBTTFT: noticeable
  • • Partial CPU offload: ~41% of layers run on CPU
ollama run command-r:35b
20
tok/s
Estimated
Weights
21.00 GB
KV cache
17.50 GB
Activations
1.06 GB
Runtime
1.00 GB
Time to first token (prefill, 512-token prompt): ~730 ms (noticeable)
Model details →

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

+32 GB system RAM

~$80–150

Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 41 new comfortable, 73 new tradeoff

  • • Qwen 3 0.6B
  • • Qwen 3 1.7B
  • • Gemma 3 270M
  • • SmolLM2 135M Instruct
Shop this upgrade↗

Upgrade to AMD Instinct MI210

see current pricing

64 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~960 GB/s to ~1638 GB/s.

Unlocks: 112 new comfortable

  • • Qwen 3 0.6B
  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen3.6 27B
Shop this upgrade↗

Add a second AMD Radeon RX 7900 XTX

~$899

Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.

Unlocks: 94 new comfortable

  • • Qwen 3 0.6B
  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen3.6 27B
Shop this upgrade↗

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)
1600B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.

—
DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.

—
Llama 4 Scout
109B
llama
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.

—

How to read these numbers

Measured here
Measured here - RunLocalAI ran this exact combo on owner hardware with public evidence.

Source-backed
Source-backed / community - a reproduced public source supports the speed, but it is not labeled as owner-measured.

Extrapolated
Extrapolated - predicted from a measured benchmark on similar-bandwidth hardware.

Estimated
Estimated - formula based on VRAM bandwidth and model architecture; not a benchmark row.

RunLocalAI Will-It-Run Framework →

Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.