FitMyLLM
INTEL· XE-HPG

Intel Arc A570M

Running LLMs on the Arc A570M — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
8 GB
ENTRY-LEVEL
BANDWIDTH
224
GB/S
MODELS Q4
201/449
45%
7B Q4 SPEED
~10
USABLE
▸ MODEL COVERAGE @ Q445% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
~24
TOK/S
7B
~10
TOK/S
14B
7.9GB NEEDED
32B
18.0GB NEEDED
70B
39.4GB NEEDED
▸ MEASURED RIG REPORTS

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

SEE THE REPORTS
▸ SPECIFICATIONS
VRAM
8 GB
BANDWIDTH
224 GB/s
FP16 COMPUTE
10.7 TFLOPS
TDP
75W
MEMORY
GDDR6
ARCHITECTURE
Xe-HPG
COMPUTE UNITS
128
PCIE
Gen 4 x8
63
FAST MODELS · >30 TOK/S
Real-time chat speed
151
USABLE · >10 TOK/S
Comfortable for all tasks
201
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test Arc A570M (or anything bigger) without committing. Pay by the second, cancel anytime.

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 201
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
796
TOK/S · 7% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
531
TOK/S · 7% VRAM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
512
TOK/S · 7% VRAM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
512
TOK/S · 7% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
280
TOK/S · 8% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
265
TOK/S · 8% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
235
TOK/S · 8% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
214
TOK/S · 9% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
214
TOK/S · 9% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
214
TOK/S · 9% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
205
TOK/S · 9% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
199
TOK/S · 9% VRAM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
189
TOK/S · 9% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
143
TOK/S · 10% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
143
TOK/S · 10% VRAM
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
138
TOK/S · 10% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
126
TOK/S · 10% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
126
TOK/S · 10% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
119
TOK/S · 11% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
119
TOK/S · 11% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
119
TOK/S · 11% VRAM
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
116
TOK/S · 11% VRAM
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
97
TOK/S · 12% VRAM
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
96
TOK/S · 12% VRAM
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
88
TOK/S · 12% VRAM
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
82
TOK/S · 13% VRAM
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
76
TOK/S · 13% VRAM
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
66
TOK/S · 14% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
65
TOK/S · 15% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
60
TOK/S · 15% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
60
TOK/S · 15% VRAM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
60
TOK/S · 15% VRAM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
60
TOK/S · 15% VRAM
A
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
55
TOK/S · 16% VRAM
A
OPT 1.3B1.3B
OPT·2K CTX· CHAT
55
TOK/S · 16% VRAM
A
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
55
TOK/S · 16% VRAM
A
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
53
TOK/S · 16% VRAM
A
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
50
TOK/S · 17% VRAM
A
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
50
TOK/S · 17% VRAM
A
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
48
TOK/S · 70% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Arc A570M.

WHAT THIS CARD IS WORTH

Arc A570M holds 201 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is Falcon3-10B at IQ4_XS.

TOKENS/SEC PER $100
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
what memory costs on this card
THE BIGGEST IT TAKES
Falcon3-10B10.3B · IQ4_XS7.1 GB7 tok/sEST
Bamba 9B v29.78B · Q4_K_M7.2 GB7 tok/sEST
RecurrentGemma 9B9.63B · Q4_K_M6.8 GB7 tok/sEST
glm-4-9b9.4B · Q4_K_M6.6 GB7 tok/sEST
Yi 1.5 9B9B · Q4_K_M6.5 GB7 tok/sEST
Yi Coder 9B9B · Q4_K_M6.5 GB7 tok/sEST
Ministral 3 8B8.92B · Q4_K_M6.6 GB7 tok/sEST
Ministral 3 8B Reasoning8.92B · Q4_K_M6.6 GB7 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M3 Pro (18GB)12 GB$1,5991.5 tok/s per $100
M1 Pro (16GB)11 GB$9992.9 tok/s per $100
M2 Pro (16GB)11 GB$1,2992.2 tok/s per $100
M4 (16GB)11 GB$4994.0 tok/s per $100
Arc A570M8 GB

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

▸ DEVICE UNDER TEST

Intel Arc A570M — 8 GB VRAM.

ARC A570M SPEC
BRAND
Intel
VRAM
8 GB GDDR6
BANDWIDTH
224 GB/s
FP16 COMPUTE
10.7 TFLOPS
FP32 COMPUTE
5.3 TFLOPS
TDP
75 W
ARCHITECTURE
Xe-HPG
▸ AI CAPABILITY
201/ 449 models @ Q4

With 8 GB VRAM and 224 GB/s bandwidth, this GPU handles models up to 9.63B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~26 tok/s.

RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR ARC A570M
201 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
RecurrentGemma 9B9.63B6.4 GB735.0
glm-4-9b9.4B6.2 GB820.5
gemma-2-9b9.2B6.1 GB830.2
Yi 1.5 9B9B6.0 GB830.3
Yi Coder 9B9B6.0 GB835.8
Ministral 3 8B8.92B5.9 GB825.7
Ministral 3 8B Reasoning8.92B5.9 GB8
NVIDIA-Nemotron-Nano-9B-v28.9B5.9 GB844.2
InternLM3 8B Instruct8.8B5.9 GB838.7
Gemma 1 7B8.54B5.7 GB824.7
CodeGemma 7B8.54B5.7 GB840.2
LFM2 8B A1B8.3B5.6 GB4824.3
Seed-Coder 8B Instruct8.25B5.5 GB934.1
Seed-Coder 8B Reasoning8.25B5.5 GB932.9
DeepSeek R1-0528 Qwen3 8B8.2B5.5 GB936.3
Qwen3-8B8.2B5.5 GB943.3
Granite 3.0 8B8.17B5.5 GB936.4
Granite 3.1 8B8.17B5.5 GB938.6
Command-R7B8.03B5.4 GB935.3
Aya Expanse 8B8B5.4 GB927.8